探索全球前沿学术脉络

01.

bioRxiv (Bioinfo) 2026-06-22 DOI: HASH:f292ec377589f4542c6399647724eb75

From hotspot dependence to distributed robustness in resistance-aware lead optimization

作者:

Wang↗Xiao↗Kang↗Cui↗Fu↗Li↗Perea↗S. E↗Han↗

Drug resistance remains a recurrent failure mode in targeted anticancer and antiviral therapy, and resistance evidence often enters only after compound selection. ResistAgent is an evidence-constrained framework that converts mutational liabilities into design-time objectives through site- and combo-aware resistance mapping, deterministic mechanism diagnosis and robust counter-design. In EGFR-Erlotinib and HIV-RT-Rilpivirine, the framework separated residue-level liabilities from observed HIV combination liabilities and linked prioritized mutations to anchor loss, pocket rearrangement, electrostatic shifts and contact redistribution. Same-budget paired searches showed that robust objectives changed lower-tail mutant-panel behavior and interaction-dependence profiles while prioritizing robustness over average-affinity behavior. Under predefined liability panels, selected robust-best trajectories shifted support away from mutable hotspot contacts toward more distributed interaction networks. Supplementary physical summaries and ranking-first benchmarks support the scope of this resistance-aware design strategy while preserving clear boundaries for prospective validation.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19894

Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures

作者:

Xinhe Mu↗Zaijiu Shang↗Zhaoqi Zhou↗Chuan Zhou↗Qi Meng↗Guiying Yan↗Zhiming Ma↗

arXiv:2606.19894v1 Announce Type: new Abstract: The remarkable success of score-based diffusion models has spurred significant efforts to establish their theoretical foundations. However, existing complexity bounds for score approximation rely heavily on restrictive assumptions like Lipschitz continuous densities or smooth manifold supports, which are routinely violated by the singularities, sharp boundaries, and disjoint clusters inherent to real-world perceptual data. This work establishes a universal score approximation theorem that works for any distribution supported on any compact set of upper Minkowski dimension $d$. Using a novel discrete-mixture formulation, we prove that the score function can be approximated with a ReLU network whose complexity grows exponentially only with $d$, thus breaking the exponential curse of ambient dimensionality. Combined with existing theories on accurately solving the backward diffusion SDE for arbitrary compact distributions, our work shows that diffusion models readily adapt to irregular, non-smooth data structures, explaining their competence in real-world generative tasks.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.05014

Depth-Attention: Cross-Layer Value Mixing for Language Models

作者:

Boyi Zeng↗Yiqin Hao↗Zitong Wang↗Shixiang Song↗He Li↗Feichen Song↗Yifan Liu↗Ziwei He↗Xinbing Wang↗Zhouhan Lin↗

Self-attention selects information freely across the sequence, but across depth, Transformers merely add each layer's output to the residual stream, so later layers cannot selectively reuse earlier-layer representations. Recent cross-layer methods improve this flow but operate on hidden states outside attention, adding state beyond the key-value cache at inference–a cost that becomes increasingly salient as modern LLMs compress the cache with grouped-query and multi-head latent attention. We introduce Depth-Attention, which performs this selection inside the attention module itself: before a layer attends over the sequence, its query attends over the keys of earlier layers at the same token position and mixes their values into the value that self-attention then reads. Because Depth-Attention reuses the standard attention queries, keys, and value-cache slots, storing depth-mixed values in place of the original values, it adds no parameters and introduces no persistent inference state beyond the standard key-value cache–the same cache size as a vanilla decoder and less than hidden-state-based cross-layer methods. On Qwen3-style decoders at 1.5B and 3B parameters, Depth-Attention attains the lowest perplexity and the highest average downstream accuracy, improving over the vanilla Transformer by up to 2.3 accuracy points and surpassing strong cross-layer baselines in perplexity and average accuracy, while adding under 0.01% extra arithmetic FLOPs and no additional persistent inference state. The gains hold from 360M to 3B parameters and extend to looped Transformers.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.19528

Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices

作者:

Hassan Dbouk↗Matthias Reisser↗Prathamesh Mandke↗Likhita Arun Navali↗Christos Louizos↗

arXiv:2606.19528v1 Announce Type: cross Abstract: Fine-tuning of Large Language Models (LLMs) using Low-Rank Adaptation (LoRA) on an end-user's data offers personalized experiences while keeping data private, but faces severe memory constraints on consumer hardware. Peak memory during fine-tuning often exceeds device limits, especially for models with billions of parameters and long-context training data. This paper introduces a suite of complementary techniques to reduce memory footprint without sacrificing model quality: (1) base model quantization with on-the-fly dequantization, (2) memory-efficient checkpointing combining selective activation caching and disk offloading, (3) softmax approximation using semantically relevant token subsets, and (4) logits masking. Experiments on Llama-3.2 3B and Qwen-2.5 3B demonstrate up to $26\times$ and $28\times$ reduction in peak memory, enabling fine-tuning on resource-constrained devices.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2606.11891

Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation

作者:

Mehmet Turan Yard{\i}mc{\i}↗

arXiv:2606.11891v1 Announce Type: cross Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a single policy. A natural design choice is whether to use a single (unified) critic that estimates the combined value of all objectives, or separate (dual) critics with disjoint reward signals. We present a controlled comparison on the Unitree G1 humanoid (23 active DoF) in NVIDIA Isaac Lab, training loco-manipulation policies through a sequential curriculum spanning 13 levels from stationary reaching to walking with variable-orientation targets. In standardized evaluation, dual-critic policies reach targets 3.5$\times$ faster (6.5 vs. 22.6 simulation steps), achieve 2$\times$ higher throughput (14.3 vs. 7.0 validated reaches per 1,000 steps), and attain higher validated reach rates (65.2% vs. 53.8%) compared to the unified-critic policy. Notably, additional anti-gaming reward mechanisms provide no further improvement beyond the architectural change alone (60.9% vs. 65.2%). These results have direct implications for the emerging paradigm of RL fine-tuning of imitation-learned policies: when refining a pre-trained manipulation policy with RL, a unified critic risks suppressing the learned behavior through competing locomotion gradients. These findings demonstrate that critic architecture is a primary - and often overlooked - design choice in multi-objective humanoid RL, with greater impact than reward engineering on reaching efficiency.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14565

CANN-EUCLID: unsupervised constitutive artificial neural network model discovery from full-field data

作者:

Benjamin Alheit↗Siddhant Kumar↗Mathias Peirlinck↗

arXiv:2606.14565v1 Announce Type: cross Abstract: Constitutive artificial neural networks (CANNs) provide interpretable material model discovery, but have so far been used in stress-supervised settings based on apparent stress-strain data from homogeneous tests. Because each test samples only a narrow loading path and provides homogenized rather than local stress information, robust discovery typically requires multiple loading modes to constrain the multidimensional response. This is challenging for soft biological tissues, where repeated testing, damage, and sample variability limit reliable information from a single specimen. Here, we combine CANNs with the stress-unsupervised full-field discovery framework EUCLID to identify sparse hyperelastic laws directly from displacement fields and reaction forces in one heterogeneity-inducing loading case. CANN-EUCLID minimizes equilibrium imbalance with sparsity-promoting regularization selecting compact active terms, without local stress measurements or a prescribed law. We evaluate the approach on isotropic and anisotropic benchmarks with prescribed ground-truth laws. When the ground truth is representable by the chosen CANN basis, our method recovers the correct terms with near-exact accuracy, including exponential terms with embedded parameters. When it is not contained in the basis, the method retains shared terms and approximates missing contributions using available basis functions. Generalization depends strongly on sampled deformation states: exponential strain-stiffening terms can be recovered accurately when sufficiently probed, but can produce large extrapolation errors when the stiffening regime lies outside the sampled domain. Forward FE validation simulations show that the discovered behavior accurately replicates the ground truth. These results establish stress-unsupervised CANN discovery as a promising framework for interpretable full-field constitutive model identification.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12200

Implicit Neural Representations of Individual Behavior

作者:

Andrew Kang↗Priya Narasimhan↗

arXiv:2606.12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data. Each episode is generated by a fixed policy, but policy labels are unavailable. This setting appears in robotics play, demonstrations, games, racing, and other datasets where heterogeneous behaviors are mixed without annotations. We introduce Behavioral INR, a self-supervised generative model that adapts implicit neural representations (INRs) from vision to behavior. Instead of mapping coordinates to RGB values, Behavioral INR represents a policy as a state-action function mapping states to subsequent actions. An episode-level latent modulates this function through FiLM layers, yielding a generative prior over policies and allowing policy identity to be inferred without supervision. Because INRs treat each datapoint as samples from an underlying function, the same model naturally accommodates variable episode lengths and different sampling granularities, as in vision INRs with different image resolutions. We also define policy-level out-of-distribution (OOD) shifts along state-distribution and action-distribution axes, which arise when policies overlap in states or actions but are not captured by standard behavioral OOD settings based only on new agents or environments. We evaluate on synthetic Gaussian random field data, MuJoCo demonstrations with controlled OOD splits, and real-world chess, Formula 1 racing, robotics, and Seek-Avoid datasets. Behavioral INR most consistently improves policy identifiability in the hardest continuous state-action settings, especially when longer episodes, more policies, and OOD splits reduce the usefulness of marginal shortcuts; amortized history encoders remain competitive when policy identity can be recovered from symbolic repetition or low-dimensional action statistics. We release code and checkpoints.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2504.11320

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints

作者:

Ruicheng Ao↗Gan Luo↗David Simchi-Levi↗Xinshang Wang↗

arXiv:2504.11320v4 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires token-by-token inference, making GPU scheduling central to latency, capacity, and cost. The difficulty is endogenous memory growth: generated tokens expand the Key-Value (KV) cache, and overflow can evict in-progress requests and waste prior computation. We formulate inference as a multi-stage online scheduling problem with endogenous memory growth, linear iteration times, and GPU-resident KV-cache constraints. We introduce a fluid model that characterizes equilibrium batch composition, memory requirement, and stability region. Guided by the fluid model, we design WAIT (Waiting for Accumulated Inference Threshold), a threshold-based admission rule for known output lengths, and Nested WAIT, which extends the rule to unknown output lengths by regulating how requests advance across decode-stage segments. Both algorithms approximate the fluid benchmark asymptotically under the stated memory conditions. Nested WAIT uses an additional safety buffer of moderate scale to hedge against memory-overflow-induced evictions under unknown output lengths. In Vidur simulations configured for Llama-2-7B on an A100 GPU, with supplemental real-GPU validation reported in the appendix, the policies enlarge the empirically observed stable operating range relative to widely used baseline algorithms and reduce latency especially in near-overloaded and overloaded regimes.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2605.04267

QUIVER: Cost-Aware Adaptive Preference Querying in Surrogate-Assisted Evolutionary Multi-Objective Optimization

作者:

Florian A. D. Burnat↗

arXiv:2605.04267v2 Announce Type: replace Abstract: Interactive multi-objective optimization systems face a budget allocation dilemma: one can spend resources on expensive objective evaluations or on eliciting decision-maker preferences that identify the relevant region of the Pareto set. Moreover, preference elicitation itself spans modalities with different information content and cognitive burden, ranging from cheap, noisy pairwise preference statements (PS) to richer but costlier indifference adjustments (IA). We study cost-aware optimization under an unknown scalarization and introduce QUIVER (Query-Informed Value Estimation for Regret), a surrogate-assisted evolutionary multi-objective optimizer that adaptively chooses between objective evaluations and heterogeneous preference queries. At each step, QUIVER selects the next action by maximizing the expected decision-quality improvement per unit total cost. Across DTLZ and WFG benchmarks under synthetic decision-maker models, QUIVER achieves the lowest final utility regret on challenging WFG problems (utility regret of 2.14 on WFG4, 2.82 on WFG9: a 25% improvement over baselines), outperforming all single-modality baselines. We analyze how the optimal mix of PS and IA adapts to problem difficulty: on easy problems (DTLZ2), QUIVER selects 80\% PS queries; on hard problems (WFG9), it shifts to 35% IA queries. This adaptive modality selection demonstrates cost-aware preference learning in action.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2602.04879

Rethinking the Trust Region in LLM Reinforcement Learning

作者:

Penghui Qi↗Xiangxin Zhou↗Zichen Liu↗Tianyu Pang↗Chao Du↗Min Lin↗Wee Sun Lee↗

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio clipping mechanism in PPO is structurally ill-suited for the large vocabularies inherent to LLMs. PPO constrains policy updates based on the probability ratio of sampled tokens, which serves as a noisy single-sample Monte Carlo estimate of the true policy divergence. This creates a sub-optimal learning dynamic: updates to low-probability tokens are aggressively over-penalized, while potentially catastrophic shifts in high-probability tokens are under-constrained, leading to training inefficiency and instability. To address this, we propose Divergence Proximal Policy Optimization (DPPO), which substitutes heuristic clipping with a more principled constraint based on a direct estimate of policy divergence (e.g., Total Variation or KL). To avoid huge memory footprint, we introduce the efficient Binary and Top-K approximations to capture the essential divergence with negligible overhead. Extensive empirical evaluations demonstrate that DPPO achieves superior training stability and efficiency compared to existing methods, offering a more robust foundation for RL-based LLM fine-tuning. Our code is available at https://github.com/sail-sg/Stable-RL.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15307

Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

作者:

Mohamed Bayan Kmainasi↗Mucahid Kutlu↗Ali Ezzat Shahroor↗Abul Hasnat↗Firoj Alam↗

Hateful and propagandistic memes exploit the interplay between images and text to convey harmful intent that neither modality reveals alone. Although thinking-based multimodal large language models (MLLMs) have advanced vision-language understanding, their application to meme content moderation remains underexplored. We propose a reinforcement learning-based post-training method that improves classification performance and reference-based explanation quality in thinking-based MLLMs via task-specific rewards and Group Relative Policy Optimization (GRPO). Concretely, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful and propagandistic meme understanding across English and Arabic benchmarks, (ii) extend existing meme datasets with weakly supervised chain-of-thought (CoT) rationales via distillation and multi-LLM fine-grained propaganda annotations, (iii) introduce a GRPO-based objective with thinking-length regularization that jointly optimizes classification accuracy and explanation quality, and (iv) investigate self-supervised GRPO on unlabeled memes using consensus-based pseudo-labels. Experiments on the Hateful Memes and ArMeme benchmarks show that our approach improves over previously reported results on FHM accuracy (up to +2.1%, from 79.9% to 82.0%) and on ArMeme macro-F1 (up to +7.6 points, from 0.536 to 0.612 with explanations; +6.1 compared to the original ArMeme benchmark), while also generating natural-language explanations. On ArMeme, sequence-classification baselines remain stronger in terms of raw accuracy, whereas our approach provides more balanced per-class performance along with explanations. We publicly release our code, data extensions, and evaluation resources.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2502.14894

FOCUS on Contamination: Hydrology-Informed Noise-Aware Learning for Geospatial PFAS Mapping

作者:

Jowaria Khan↗Alexa Friedman↗Sydney Evans↗Rachel Klein↗Runzi Wang↗Katherine E. Manz↗Kaley Beins↗David Q. Andrews↗Elizabeth Bondi-Kelly↗

Per- and polyfluoroalkyl substances (PFAS) are persistent environmental contaminants with significant public health impacts, yet large-scale monitoring remains severely limited due to the high cost and logistical challenges of field sampling. The lack of samples leads to difficulty simulating their spread with physical models and limited scientific understanding of PFAS transport in surface waters. Yet, rich geospatial and satellite-derived data describing land cover, hydrology, and industrial activity are widely available. We introduce FOCUS, a geospatial deep learning framework for PFAS contamination mapping that integrates sparse PFAS observations with large-scale environmental context, including priors derived from hydrological connectivity, land cover, source proximity, and sampling distance. These priors are integrated into a principled, noise-aware loss, yielding a robust training objective under sparse labels. Across extensive ablations, robustness analyses, and real-world validation, FOCUS consistently outperforms baselines including sparse segmentation, Kriging, and pollutant transport simulations, while preserving spatial coherence and scalability over large regions. Our results demonstrate how AI can support environmental science by providing screening-level risk maps that prioritize follow-up sampling and help connect potential sources to surface-water contamination patterns in the absence of complete physical models.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19559

Uncertainty Decomposition for Clarification Seeking in LLM Agents

作者:

Gregory Matsnev↗

Recent position papers argue that the classical aleatoric/epistemic uncertainty framework is insufficient for interactive large language model (LLM) agents and call for underspecification-aware, decomposed, and communicable uncertainty representations that can unlock new agent capabilities such as proactive clarification seeking and shared mental-model building. Practical deployment constraints – black-box APIs, interactive latency budgets, and the absence of labeled trajectories – rule out logprob-based, multi-sampling, and training-based methods, leaving prompt-based estimation as the most viable family for surfacing such signals at deployment time. We answer this call with a simple prompt-based decomposition that separates action confidence from request uncertainty (u), enabling the agent to ask for clarification when the task specification is ambiguous. To evaluate it, we introduce two clarification-augmented benchmarks (WebShop-Clarification and ALFWorld-Clarification) in which 50% of tasks are deliberately underspecified, and systematically compare the proposed decomposition against ReAct+UE and Uncertainty-Aware Memory (UAM) across five LLM backbones (GPT-5.1, DeepSeek-v3.2-exp, GLM-4.7, Qwen3.5-35B, GPT-OSS-120B) on these variants together with the standard WebShop, ALFWorld, and REAL benchmarks for fault detection. Averaged across the five backbones, the proposed decomposition improves clarification F1 on ALFWorld-Clarification by 73% over ReAct+UE and by 36% over UAM, and leads clarification F1 on every backbone on WebShop-Clarification and on four of five backbones on ALFWorld-Clarification, indicating that the gains generalize beyond a single LLM.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13625

Revisiting Vehicle Color Recognition in Long-Tailed Surveillance Scenarios

作者:

Vin\'icius Orr\'u↗Bruno H. Foggiatto↗Gabriel E. Lima↗David Menotti↗Rayson Laroca↗

Vehicle color recognition is an important cue for vehicle identification in surveillance systems, especially when license plates are illegible due to low resolution, occlusion, motion blur, or poor illumination. However, real-world vehicle color distributions are highly imbalanced, making overall accuracy insufficient to assess performance on rare but operationally relevant colors. This paper presents a comprehensive study of vehicle color recognition under severe class imbalance using UFPR-VeSV, a challenging real-world surveillance dataset. We investigate synthetic minority-class augmentation through two off-the-shelf generative strategies: text-conditioned image generation with RunDiffusion/JuggernautXL and image-conditioned color editing with Gemini 2.0 Flash. The curated synthetic data are combined with modern visual representations, loss reweighting, learning-rate scheduling, color-safe augmentation, foreground-aware preprocessing, and ensemble fusion. The bestperforming approach achieves 94.6% micro accuracy and 79.7% macro accuracy, improving macro accuracy by 8.2 percentage points over recent literature. A manual error analysis further shows that many remaining failures are visually ambiguous even for human annotators, highlighting the practical limits of color-based vehicle identification in unconstrained surveillance imagery. The generated images and source code are publicly available at https://github.com/viniciusorru/vcr-synthetic

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.04009

Counterfactual Explanations for Deep Two-Sample Testing

作者:

Wei-Cheng Lai↗Marco Simnacher↗Christoph Lippert↗

arXiv:2606.04009v2 Announce Type: replace-cross Abstract: Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective on high-dimensional structured data such as images. Recent deep two-sample tests improve sensitivity in these settings by learning informative representations, yet they provide limited insight into which data features drive rejection of the null hypothesis $H_0$. To address this issue, we propose a counterfactual explanation framework for deep two-sample testing that generates sample-level edits moving observations from a source group toward a target group while explicitly reducing the discrepancy measured by the test. Our method combines a diffusion autoencoder with a pretrained deep two-sample test model and optimizes a maximum mean discrepancy (MMD) objective in the test model's representation space to produce plausible counterfactuals. We quantify distribution-level effects through changes in the test statistic and the resulting two-sample p-values. We evaluate the method on synthetic 2D shape datasets and two MRI cohorts. Across both settings, the counterfactual transformations consistently increase p-values relative to the original samples, indicating that the edited source set becomes statistically closer to the target distribution under the test. We measure minimality using LPIPS to ensure the counterfactuals remain close to the original samples. The resulting edits provide interpretable evidence of the features associated with the detected group differences. On MRI, the localized changes are consistent with known anatomical differences between cohorts.

阅读与讨论 → 访问原文 →

16.

arXiv (math.PR) 2026-06-18 DOI: arXiv:2606.08304

Functions of Bounded Variation and Point Processes

作者:

J. Antezana↗M. Levi↗J. Marzo↗J. Ortega-Cerd\`a↗

arXiv:2606.08304v2 Announce Type: replace-cross Abstract: We investigate the relationship between the analytical properties of functions of bounded variation and the statistical behavior of hyperuniform point processes. We establish several characterization formulas for the jump part of the gradient of a bounded variation function, extending and unifying previous results by Beretti–Gennaioli and Dávila. In particular, we provide new expressions for the $L^2$-jump of the gradient using both difference quotients and Fourier transform methods. Furthermore, we connect these analytic structures to the theory of hyperuniform point processes. By analyzing the variance of linear statistics associated with bounded variation functions, we provide asymptotic estimates that depend on the specific classification of the hyperuniformity of the point process. The results show how the regularity and jump discontinuities of a function dictate the growth rate of fluctuations in point processes. Finally, we introduce an averaged quadratic BMO-type oscillation functional over translated and rotated cube partitions, similar to the one recently studied by Ambrosio et al., and prove, using results from point process, that it converges to an explicit dimensional constant times the $L^2-$jump, giving in particular a further new characterization of the perimeter of a set.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2604.03156

CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator

作者:

Yuhan Pu↗Hao Zheng↗Ziqian Mo↗Zirui Pang↗Hill Zhang↗Tianyi Fan↗Shuhong Wu↗Jiaheng Wei↗

Conditional image editing aims to modify a source image according to textual prompts and optional reference guidance. Such editing is crucial in scenarios requiring strict structural control (i.e., anomaly insertion in driving scenes and complex human pose transformation). Despite recent advances in large-scale editing models (i.e., Seedream, Nano Banana, etc), most approaches rely on single-step generation. This paradigm often lacks explicit quality control, may introduce excessive deviation from the original image, and frequently produces structural artifacts or environment-inconsistent modifications, typically requiring manual prompt tuning to achieve acceptable results. We propose CAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process rather than a one-shot generation task. CAMEO decomposes editing into coordinated stages of planning, structured prompting, hypothesis generation, and adaptive reference grounding, where external guidance is invoked only when task complexity requires it. To overcome the lack of intrinsic quality control in existing methods, evaluation is embedded directly within the editing loop. Intermediate results are iteratively refined through structured feedback, forming a closed-loop process that progressively corrects structural and contextual inconsistencies. We evaluate CAMEO on anomaly insertion and human pose switching tasks. Across multiple strong editing backbones and independent evaluation models, CAMEO consistently achieves 20\% more win rate on average compared to multiple state-of-the-art models, demonstrating improved robustness, controllability, and structural reliability in conditional image editing.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2602.02355

Mitigating Heterogeneity-Induced Drift in Hierarchical Sign-Based Federated Learning

作者:

Amirreza Kazemi↗Seyed Mohammad Azimi-Abarghouyi↗Gabor Fodor↗Carlo Fischione↗

arXiv:2602.02355v2 Announce Type: replace-cross Abstract: Hierarchical federated learning (HFL) is well suited for large-scale wireless and Internet of Things systems, where devices communicate with nearby edge servers before reaching the cloud. In these environments, uplink bandwidth and latency impose strict communication constraints, making aggressive gradient compression essential. One-bit sign-based stochastic gradient descent methods provide an attractive solution in flat federated settings, but their behavior in hierarchical edge–cloud architectures remains insufficiently understood, especially under inter-cluster data heterogeneity. To address this gap, we develop a sign-based HFL framework in which devices transmit binary stochastic-gradient signs to edge servers, edge servers apply majority voting, and the cloud periodically aggregates edge models. Our analysis reveals that inter-cluster heterogeneity induces a persistent bias term in the convergence bound, reflecting the drift of edge models toward local objectives. This term cannot be removed by increasing the number of training rounds or by tuning standard hyperparameters alone. We therefore propose \(\mathtt{DC-HierSignSGD}\), a drift-corrected sign-based HFL algorithm in which devices apply a cloud-assisted gradient correction before taking the sign. We show that this pre-sign correction mitigates the non-vanishing heterogeneity-induced bias while preserving binary device–edge communication during the repeated local sign-update steps. Experiments under severe inter-cluster heterogeneity demonstrate that \(\mathtt{DC-HierSignSGD}\) improves the stability and accuracy of sign-based HFL and achieves performance comparable to full-precision hierarchical SGD with substantially lower device–edge communication.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13710

Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher

作者:

Hongming Piao↗Chi Liu↗Mengzhuo Chen↗Yan Shu↗Derek Li↗Ying Wei↗Bryan Dai↗

arXiv:2606.13710v1 Announce Type: new Abstract: Deep research and agent evolution serve as de-facto tasks for AI agents in real-world applications toward artificial general intelligence. The former enables autonomous retrieval and integration of information in open-ended environments to tackle open-ended research tasks, yet it is constrained by the static parametric deep research capabilities of agent systems. The latter allows agents to autonomously interact with the environment to gain experiences that evolve model capabilities. However, its effectiveness has been widely validated only on verifiable tasks with standard answers, leaving a gap with open-ended research tasks. To bridge these two critical tasks, we propose the Hybrid Open-Ended Tri-Evolution (HOTE) framework, which leverages hybrid-mode reinforcement learning to facilitate the collaborative evolution of a proposer, solver and judge based on web-scale knowledge, moving toward autonomous evolving agents in open-ended tasks and environments. Extensive experiments on three long-form deep research benchmarks demonstrate that the 8B model trained via HOTE surpasses the strongest static open 8-32B models as well as those trained by state-of-the-art deep research training methods with less time overhead, and further verify that the evolution of all three modules in HOTE is indispensable.

阅读与讨论 → 访问原文 →

20.

Nature Medicine 2026-06-15 DOI: HASH:b6385f415613a1900ec57d2a3b0534e2

Long-term independent use of an intracortical brain–computer interface for speech and cursor control

作者:

Nicholas S. Card↗

Brain–computer interfaces (BCIs) can provide naturalistic communication and digital access to people with severe paralysis by decoding neural activity associated with attempted speech and movement. Recent work has demonstrated highly accurate intracortical BCIs for speech and cursor control, but two critical capabilities needed for practical viability were unmet: independent at-home operation without researcher assistance and reliable long-term performance supporting accurate speech and cursor decoding. Here we demonstrate the independent and near-daily use of a multimodal BCI with novel brain-to-text speech and computer cursor decoders by a man with paralysis and severe dysarthria due to amyotrophic lateral sclerosis. Over nearly 2 years, the participant used the BCI for more than 3,800 h at home with no researchers present to maintain rich interpersonal communication with his family and friends, independently control his personal computer and sustain full-time employment—despite being paralyzed. He communicated 183,060 sentences—totaling 1,960,163 words—at an average rate of 56 words per minute. He labeled 92% of sentences as being decoded at least mostly correctly. In formal quantifications of performance where he was asked to say words presented on a screen, attempted speech was consistently decoded with more than 99% word accuracy (125,000 word vocabulary). The participant also used the speech BCI as keyboard input and the cursor BCI as mouse input to control his personal computer, enabling him to send text messages and emails and to browse the internet. These results demonstrate that intracortical BCIs have the potential to support independent use in the home, marking a critical step toward practical assistive technology for people with severe motor impairment. An automated intracortical brain–computer interface, used at home with no researcher intervention, provides long-term and accurate restoration of speech-based communication and cursor-based computer usage in a person with severe dysarthria due to amyotrophic lateral sclerosis.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2504.15610

Fine-Tuning a 7B Advisor on Free-Tier GPUs: An Adapter-Handoff Recipe and a Synthetic-Data Reliability Caution

作者:

Md Millat Hosen↗

arXiv:2504.15610v4 Announce Type: replace Abstract: Fine-tuning a 7B language model for specialized advising is attractive in resource-constrained settings, but multi-epoch runs routinely exceed the wall-clock limits of the free-tier GPUs (Kaggle, Colab) such users rely on. We report two things. First, a practical recipe: a three-epoch QLoRA fine-tune of Mistral-7B-Instruct-v0.3 (4-bit NF4, LoRA rank 16, via Unsloth) completed across two free-tier 16 GB GPUs (Tesla P100 then T4) by checkpointing only the small LoRA adapter (41.9M parameters) and resuming on the second machine. Adapter-only handoff is sufficient – optimizer and scheduler state need not be transferred – so the binding constraint is per-step VRAM and per-session wall-clock, not aggregate compute. Second, and more importantly, an honest evaluation that returns a cautionary result. On a blind held-out comparison against the un-fine-tuned base model, the fine-tuned model scored higher on similarity to the synthetic training distribution (BERTScore F1 +0.063, a fidelity not quality signal) but lower on advising quality: a blind LLM-as-judge preferred the base model on 46% of prompts versus 18%, and a source-verified factuality audit found four confident errors from the fine-tuned model on policy-sensitive topics against zero for the base. Auditing the training data with the same method, we find this is not a fine-tuning artifact: each audited error is already present in the Gemini-generated training answers, and a random-sample audit finds verifiable errors in a sizable fraction of responses (28-40%; single-judge, n=40). The data is therefore sufficient to account for the errors, which we attribute to the synthetic-data pipeline rather than the adapter-handoff method. We release the dataset, adapter, cross-GPU notebooks, and full evaluation harness so every result reproduces on a single 16 GB GPU.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15162

GeoStream: Toward Precise Camera Controlled Streaming Video Generation

作者:

Yizhou Zhao↗Yifan Wang↗Xiaoyuan Wang↗Yushu Wu↗Hao Zhang↗Moayed Haji-Ali↗Rameen Abdal↗Ashkan Mirzaei↗Yanyu Li↗Willi Menapace↗Laszlo Jeni↗Sergey Tulyakov↗…

Accurate interactive camera control is essential for video-based world models, but most existing approaches learn camera motion implicitly, leading to inaccurate control under out-of-distribution trajectories. Explicit geometric conditioning improves controllability, but existing methods are non-autoregressive and rely on a static 3D cache built from an initial frame, which becomes ineffective once the viewpoint moves beyond the original frustum. We propose GeoStream, a framework that enables precise metric-scale camera control in autoregressive streaming video generation. Our method maintains a self-refreshing 3D cache that is periodically updated online from the model's own outputs: we estimate depth from the most recently generated frame, unproject to 3D, and reproject into the target view to produce point reprojections as geometric conditioning for subsequent synthesis. By the same principle, the conditioning seen during training is also rendered from the student's own generated frames, yielding a fully on-policy distillation that naturally aligns the train and inference conditioning distributions. Unlike prior work that uses off-policy condition noising, our approach trains the model against the exact error distribution it encounters at inference, mitigating both standard autoregressive drift and the second-order geometric feedback loop that arises when the cache itself is derived from generated outputs. Quantitative and qualitative results show that our approach substantially improves camera controllability.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2410.24145

Projected random forests and conformal prediction of circular data

作者:

Paulo C. Marques F↗Rinaldo Artes↗Helton Graziadei↗

arXiv:2410.24145v3 Announce Type: replace-cross Abstract: We apply conformal prediction techniques to regression problems with circular responses, producing prediction sets with adaptive arc length and finite-sample coverage guarantees for any circular predictive model under the assumption of data exchangeability. Leveraging the high performance of existing predictive models designed for linear responses, we analyze a general projection procedure that converts any linear-response regression model into one suitable for circular responses. When random forests are used as base models in this projection procedure, we leverage the random forest out-of-bag mechanism to eliminate the need for a separate calibration sample in the construction of prediction sets. On synthetic and real datasets, the resulting projected random forest model produces more efficient out-of-bag conformal prediction sets, with shorter median arc length, than the split conformal prediction sets generated by two existing alternative models.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19327

Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation

作者:

Siyi Gu↗Jialin Chen↗Sophia Zhou↗Arman Cohan↗Rex Ying↗

Post-training of reasoning language models is commonly driven by supervised distillation and reinforcement learning with verifiable rewards. Distillation often relies on chain-of-thought annotations that are expensive to obtain and may themselves be noisy, incomplete, or partially incorrect; even when the final solution is correct, an imperfect rationale can interfere with learning. Reinforcement learning with verified rewards, on the other hand, typically compresses evaluative feedback into a scalar signal, obscuring which aspects of a response should be improved. We propose Rubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation. Our method conditions the teacher model on criterion-level rubrics and uses it to provide token-level guidance on the student's own sampled trajectories. This design avoids treating a single reference rationale as the sole supervision target. Instead, rubrics specify what a strong response should satisfy, enabling more fine-grained credit assignment over the reasoning process than scalar reward optimization. We instantiate this framework with a two-stage pipeline that first learns to generate task-specific rubrics and then trains a rubric-guided reasoner. We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance over the reasoning process, surpassing GRPO by 1.0 points and OPSD by 0.9 points on average.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16072

MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware Source Code Specimens

作者:

Bojing Li↗Duo Zhong↗Prajna Bhandary↗Raguvir S↗Charles Maxa↗Robert J Joyce↗Charles Nicholas↗

arXiv:2606.16072v1 Announce Type: cross Abstract: Compared with binaries and decompiled code, malware source code more directly reflects the attackers' original intent. However, the scarcity of source code and the high cost of manual review make such datasets difficult to build and maintain. We propose MASCOT-Android, a curated dataset of Android malware source code and an automated collection framework for scalable malware source code discovery on GitHub. A key finding of our work is that repository-level documentation alone provides a strong signal for malware source code collection. Our model extracts character-level TF-IDF features from 8,772 malware and 25,747 benign README documents and trains a LinearSVC classifier to distinguish malware repositories. This README-only model achieves an accuracy of 96.28\% and an FPR of 1.06\% in local evaluation. In addition, the model outputs confidence scores, allowing users to adjust the decision threshold to balance FPR and coverage, which is practical in real-world malware source code collection.

阅读与讨论 → 访问原文 →