Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (CS.CL) 2026-06-16

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $\beta$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $\beta$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

02.
arXiv (CS.AI) 2026-06-24

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

arXiv:2606.24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras – a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images. We propose G$^3$VLA, a camera-aware geometric module that injects calibrated structure into the visual-token stream of a pretrained VLA without altering its action space or imitation objective, combining intrinsic-conditioned ray embeddings, projective positional encoding (PRoPE), and bidirectional cross-view fusion. Geometric supervision is provided either from ground-truth point maps when available, or from confidence-gated $\pi^3$X teacher predictions, requiring no depth sensors or manual annotations. Instantiated on $\pi_0$, G$^3$VLA yields consistent gains across the LIBERO suites, RoboCasa24, RoboTwin2.0, and real-robot settings, with the largest improvements on spatially and object-sensitive tasks. We further validate on $\pi_{0.5}$ and GR00T 1.5, with results suggesting that geometric transfer is most effective when geometry-aware tokens have direct access to the action generation pathway. Our project page is at https://sites.google.com/view/g3vla

03.
arXiv (CS.AI) 2026-06-11

Compiler-First State Space Duality and Portable $O(1)$ Autoregressive Caching for Inference

arXiv:2603.09555v2 Announce Type: replace-cross Abstract: High-throughput Mamba-2 inference is usually tied to fused CUDA and Triton kernels, limiting portability across accelerator backends. We show that the state space duality (SSD) recurrence has a compiler-friendly structure: diagonal per-head dynamics, fixed-size chunking, einsum-dominated compute, and static control flow. Expressing this structure in standard JAX primitives gives a single-source inference path with no custom kernels, a registered JAX PyTree cache, and a compiled on-device autoregressive loop. On a single Google Cloud TPU v6e, batch-1 prefill reaches approximately 140 TFLOPS, or 15% model FLOP utilisation (MFU), the roofline ceiling for this regime, and cached decode reaches up to 64% hardware bandwidth utilisation (HBU). At a 4096-token context, cached decode is 27x–36x faster than full-prefix recomputation across five Mamba-2 checkpoints from 130M to 2.7B parameters. The same source runs unmodified on NVIDIA L40S, where cached decode remains sequence-length independent across all model scales. WikiText-103 validation perplexity matches the Triton reference mamba_ssm v2.2.2 within +/-0.0005 points, and hidden states agree to float32 rounding tolerance. Code is available at https://github.com/CosmoNaught/mamba2-jax.

04.
arXiv (CS.AI) 2026-06-17

A Neuromorphic Trigger for Efficient Audio Event Detection

arXiv:2606.17775v1 Announce Type: cross Abstract: Efficient processing of continuous audio streams remains a key challenge for real-time and resource-constrained systems. This paper introduces a neuromorphic trigger for audio event detection, based on a spiking neural network (SNN) that selectively gates input to downstream models. The proposed trigger acts as a low-cost front-end, identifying salient audio segments and forwarding only these to a more computationally intensive model for tasks such as classification. The trigger is implemented as a lightweight fully connected SNN and evaluated on two representative tasks: Anomalous Sound Detection (ASD) and Sound Event Detection (SED). For ASD, the trigger achieves a one-second segment-based F1 score of 0.97 on a class-agnostic form of the URBAN-SED dataset, demonstrating high reliability in identifying relevant audio regions. For SED, the trigger is combined with the Dang classifier on the DCASE 2017 Challenge Task 2 dataset, showing a potential $42.6\times$ reduction in FLOPs while reducing the lower bound of the event-based error rate from 0.41 to 0.25. These results highlight the potential of neuromorphic triggers as real-time, energy-efficient front-end filters, enabling substantial reductions in computational cost.

05.
arXiv (CS.LG) 2026-06-18

Learning to Annotate Delayed and False AEB Events: A Practical System for Extreme Class Imbalance and Asymmetric Label Noise

arXiv:2606.19186v1 Announce Type: cross Abstract: Autonomous Emergency Braking (AEB) optimization relies on accurately annotated real-world trigger events, particularly rare but critical delayed and false AEB triggers that expose system deficiencies. However, these minority samples comprise less than 5% of thousands of daily triggers, making manual annotation prohibitively expensive at scale. We present the first automated AEB annotation framework to address this problem. During development, we identified two fundamental challenges that severely impair delayed/false trigger annotation accuracy: (1) Extreme class imbalance where delayed/false triggers are overwhelmed by true triggers; (2) Asymmetric label noise where mislabeled majority samples (true triggers) suppress minority samples (delayed/false triggers) learning. To overcome these challenges, we propose two key innovations: (1) Specific data augmentation that synthesizes realistic samples by manipulating focal target attributes, transplanting ego-vehicle dynamics, and masking non-focal agents; (2) noise suppression using stable hardness estimation and probe-guided adaptive threshold to clean mislabeled true trigger samples. Crucially, we deploy our model as a practical annotation system with full-stack architecture, efficiently identifying critical delayed/false triggers from thousands of daily AEB events. Production results demonstrate 80% improvement in recall of delayed/false triggers and 50% reduction in manual workload. Beyond immediate gains, the system enables continuous self-improvement through accumulated high-quality annotations, establishing a necessary data foundation for on-vehicle AEB system optimization

06.
arXiv (CS.AI) 2026-06-11

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

arXiv:2606.12287v1 Announce Type: cross Abstract: The Transformer architecture is widely regarded as the most powerful tool for natural language processing, but due to a high number of complex operations, it inherently faces the issue of high energy consumption. To address this issue, we consider Spiking Neural Networks (SNNs), which are an energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their naturally event-driven approach to processing information. However, this inherently makes them difficult to train. Often, many SNN-based models circumvent this issue by converting pre-trained ANNs. More recently, attempts have been made to design directly trainable SNN-based adaptations of the Transformer model structure. Although the results showed great promise, the application field was computer vision. Moreover, the proposed model incorporates only encoder blocks. In this paper, we propose SpikeDecoder, a fully SNN-based implementation of the Transformer decoder block, for applications in natural language processing. In a series of experiments, we analyze the impact of exchanging different blocks of the ANN model with spike-based alternatives to identify trade-offs and significant sources of performance loss. We further investigate the role of residual connections and the selection of SNN-compatible normalization techniques. Besides the work on the model architecture, we formulate and compare different embedding methods to project text data into spikes. Finally, we demonstrate that our proposed SNN-based decoder block reduces the theoretical energy consumption by 87% to 93% compared to the ANN baseline.

07.
arXiv (quant-ph) 2026-06-15

Multi-entropy in random tensor networks

arXiv:2606.04470v2 Announce Type: replace-cross Abstract: We study the evaluation of Rényi multi-entropies $S^{(q)}_n$ in Random Tensor Network (RTN) states in the large bond-dimension limit. For the case of Rényi index $n=2$ and arbitrary number of parties $q$, we prove that that multi-entropies are determined by minimal multiway cuts through the network. When the minimal multiway cut is degenerate, we characterize the full minimizer set via compatible families of minimal cuts and give a criterion for all minimizers to come from ordinary cut partitions. For $n=2$, this gives a natural generalization of the minimal cut description of bipartite entanglement to multipartite systems with arbitrarily many parties. For the case of integer $n>2$, we show that the minimal multiway cut conjecture is in general not true by providing explicit counter examples for both the single random tensor and for the network built from isometric tilings. We discuss the implication for our results on the multipartite entanglement structures in RTN and holography.

08.
arXiv (CS.AI) 2026-06-25

Reward-Conditioned Attention: How Reward Design Shapes What Autonomous Driving Agents See

arXiv:2606.25127v1 Announce Type: cross Abstract: We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving. Using three Perceiver-based agents that share identical architectures and training data but differ only in their reward configurations$\unicode{x2014}$ranging from basic violation penalties to continuous proximity penalties$\unicode{x2014}$we analyze cross-attention allocation across 50 real-world scenarios from the Waymo Open Motion Dataset. A central methodological finding is that naïve pooling of timesteps across episodes substantially underestimates the attention$\unicode{x2013}$risk relationship; within-episode correlation with Fisher z-transform aggregation is the appropriate statistic and reveals a robustly positive link between collision risk and agent-directed attention. Building on this validated methodology, we demonstrate two reward-conditioned effects: agents trained with navigation rewards allocate up to $2.0\times$ more attention to GPS-path tokens than those trained with additional proximity penalties$\unicode{x2014}$and $4.7\times$ more than agents with no navigation incentive$\unicode{x2014}$revealing that reward content directly determines which scene elements the encoder prioritizes, and continuous time-to-collision penalties create a $learned vigilance prior$$\unicode{x2014}$elevated resting agent surveillance maintained throughout collision-free phases. In several scenarios, the complete-reward and minimal-reward models exhibit opposite attention$\unicode{x2013}$risk correlation directions, demonstrating that reward design can qualitatively reverse attentional strategy rather than merely modulating its magnitude. These results suggest that attention analysis is a practical diagnostic for verifying that a reward function produces the intended representational behaviour in safety-critical RL systems.

09.
arXiv (quant-ph) 2026-06-16

Quantifying Coherence-to-Entanglement Conversion Efficiency under Noisy Operations

arXiv:2606.16916v1 Announce Type: new Abstract: We investigate the noise-limited conversion of local quantum coherence into bipartite entanglement in a minimal two-qubit protocol comprising a coherent single-qubit input, an incoherent ancilla, an ideal CNOT operation, and subsequent environmental noise. Employing the $l_1$-norm of coherence and the entanglement negativity as resource quantifiers, we establish an exact closed-form correspondence between local single-qubit input coherence and the two-qubit entanglement generated in the noiseless limit, showing that the output negativity is precisely one half of the initial $l_1$-coherence. We then derive analytic expressions for the surviving entanglement and the associated coherence-to-entanglement conversion efficiency under two representative noise mechanisms: independent phase damping and global two-qubit depolarizing noise. The two channels exhibit qualitatively distinct degradation behavior. Phase damping induces a universal multiplicative suppression of the generated entanglement, yielding a coherence-independent conversion efficiency and no finite-noise entanglement sudden death. In contrast, global depolarization introduces an isotropic mixing contribution that shifts the partial-transpose spectrum, producing coherence-dependent degradation and a finite sudden-death threshold. We show that maximally coherent inputs not only maximize the entanglement generated by the CNOT protocol but also optimize its robustness against depolarizing noise. Direct density-matrix simulations validate the analytic results to numerical precision. These findings provide a compact analytic benchmark for assessing how different noise mechanisms constrain coherence-to-entanglement conversion in elementary quantum-information protocols and near-term quantum devices.

10.
arXiv (CS.CL) 2026-06-18

Learning Robust Pair Confidence for Multimodal Emotion-Cause Pair Extraction

Multimodal emotion-cause pair extraction (MECPE) requires reliable pair confidence over candidate pairs. Existing pair scorers commonly use pair-level cross entropy over valid candidates, which treats links mostly independently. This leaves the relative confidence geometry among competing causes under-constrained, allowing gold pairs to stay close to hard negatives or rely on incidental non-gold context. We study this vulnerability as pair-confidence brittleness and propose RPCL (Robust Pair Confidence Learning), a training-only framework for pair-confidence learning. RPCL encourages pair confidence to be both discriminative and stable: gold pairs are separated from row-wise hard negatives through a confidence-difference margin constraint, and clean pair predictions are aligned with predictions from a corrupted view where non-gold contextual utterance representations are partially corrupted. The original clean pair scorer and decoding pipeline are used unchanged at inference time. On ECF, MECAD, and MEC4, RPCL improves the three-seed mean Pair F1 over a matched base model by 2.58 to 2.83 percentage points in the full text-audio-video setting, and improves mean Pair AUPRC on all three datasets. Diagnostic analysis further shows larger gold-negative confidence gaps and lower margin-violation severity. These results suggest that explicitly shaping pair confidence is an effective training strategy for MECPE.

11.
arXiv (CS.AI) 2026-06-18

Towards Multi-Agent-Simulation-Based Community Note Evaluation

arXiv:2606.18268v1 Announce Type: cross Abstract: Community-based fact-checking that relies on cross-consensus is expanding rapidly on social media platforms. However, the delay and low-ratio of cross-consensus community fact-checks rated by human contributors remains a significant challenge. To address this, we first created ComRate, a large-scale dataset comprising 2.5 million community notes and over 209 million ratings sourced from $\mathbb{X}$. We then propose MultiCom, a persona-guided multi-agent rating framework for community note evaluation. MultiCom simulates diverse rater population by clustering contributors in a matrix-factorized rater space and prompting persona agents to generate structured assessments based on the official community notes rating schema. These agents output structured and explainable judgments, such as confidence, agreement signals and reasons. An out-of-fold calibrated aggregation algorithm combines features such as raw votes and diagnostic reason signals for reliable prediction. Extensive evaluations demonstrate that MultiCom outperforms alternative methods, achieving an average accuracy of 84.7% (balanced accuracy 68.3%, macro-F1 60.1%) on the evaluation set.

12.
medRxiv (Medicine) 2026-06-23

Associations Among Changes in Inflammatory Biomarkers, Pain Intensity, and Health-Related Quality of Life Following a 12-Week Aerobic Exercise Programme in Individuals with Non-Specific Chronic Low Back Pain

Abstract Background: Non-specific chronic low back pain (NSCLBP) is associated with persistent pain, reduced health-related quality of life (HRQoL), and low-grade systemic inflammation. This study examined associations among changes in inflammatory biomarkers, pain intensity, and HRQoL following a 12-week aerobic exercise programme. Methods: This secondary analysis used data from a randomized controlled trial involving 41 participants with NSCLBP (intervention, n = 21; control, n = 20). Participants received either supervised aerobic exercise plus health education or health education alone for 12 weeks. Change scores for tumour necrosis factor-alpha (TNF-), interleukin-6 (IL-6), high-sensitivity C-reactive protein (hs-CRP), pain intensity, and HRQoL domains were analysed using correlation and multiple regression analyses. Results: Improvements in IL-6 (r = 0.434, p = 0.005) and hs-CRP (r = 0.444, p = 0.004) were significantly associated with improvements in pain intensity. No significant associations were observed between biomarker changes and HRQoL domains. Treatment allocation was the strongest independent predictor of improvement in physical HRQoL ({beta} = 0.492, p = 0.017) and pain intensity ({beta} = -0.512, p = 0.006). Conclusions: Improvements in IL-6 and hs-CRP were associated with reductions in pain intensity but not with improvements in HRQoL. Treatment allocation was the strongest predictor of clinical improvement, suggesting that mechanisms beyond systemic inflammation may contribute to the benefits of aerobic exercise in NSCLBP. Keywords: non-specific chronic low back pain; aerobic exercise; inflammation; interleukin-6; high-sensitivity C-reactive protein; pain intensity; health-related quality of life.

13.
medRxiv (Medicine) 2026-06-18

Early-life Urban Environment, Nutrition, and Pubertal Timing in Southern Europe: An Exposome Analysis

Background: Urban environmental and lifestyle factors during early life may influence pubertal timing, but the combined effects of multiple environmental exposures within an exposome analytical framework remain poorly understood. Objective: To examine the association between early-life urban environmental exposures and pubertal timing, and to explore whether these exposures interact with early-life nutritional factors, namely breastfeeding duration and childhood diet quality. Methods: Data from two European population-based birth cohorts were analysed: Generation XXI (G21, Portugal; n=5263; 51.5% girls) and INfancia y Medio Ambiente (INMA, Spain; n=1019; 50.1% girls). Urban environmental exposures including indicators of air pollution, traffic, built environment, and natural spaces were estimated at 4 early-life stages at both cohorts: pregnancy (INMA only), birth, 1 year, and 4-5 years of age. Pubertal development timing was assessed using Tanner staging and/or the Pubertal Development Scale (PDS), and age at menarche was self-reported. Exposome-Wide Association Study (ExWAS) models and unsupervised clustering followed by ordinal logistic regression models were used to examine single- and multi-exposure associations, respectively. Regression models were fitted adjusting for relevant child characteristics, maternal factors, and household socioeconomic conditions, and corrected for multiple testing. Results: Individuals living in more unfavourable urban environments characterised by higher building density, air pollution, and lower access to natural spaces showed earlier pubertal timing according to multiple outcomes, across multiple early-life exposure periods, and in both cohorts. In the G21 cohort, these environmental profiles were associated with earlier age at menarche, particularly for exposures at 1-1.5 and 4-5 years (e.g., 1-1.5y: {beta}=-0.172, FDR-adjusted p-value=0.041), while in the INMA cohort, boys exposed to more unfavourable environmental profiles showed more advanced pubertal development, also particularly for exposures at 1-1.5 and 4-5 years of age (e.g., 1-1.5y; {beta}=0.572, FDR-adjusted p-value=0.008). Among environmental domains, air pollution and traffic were the factors most consistently associated with pubertal timing. Regarding early-life nutritional factors, longer duration of exclusive breastfeeding was associated with a lower Tanner stage among girls in G21. No significant interactions between breastfeeding duration and environmental exposure clusters were observed. Conclusion: Early-life urban environmental exposures, particularly air pollution and traffic, may influence pubertal timing. Exclusive breastfeeding may have a protective role against earlier pubertal development. These findings highlight the importance of improving urban environmental conditions and promoting breastfeeding to support healthy developmental trajectories.

14.
arXiv (CS.AI) 2026-06-16

OSGuard: A Benchmark for Safety in Computer-Use Agents

arXiv:2606.15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks. However, task success alone can miss failures in which an agent reaches the nominal goal through an unsafe shortcut. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety in computer-use agents under benign, unchanged user instructions. OSGuard contains an action-level benchmark for local guardrail decisions and a risk-augmented execution suite for end-to-end evaluation. The action-level benchmark consists of contextualized proposed actions labeled as allowed, unrelated, or unsafe, each judged relative to the original instruction and current interface state. The execution suite contains manually constructed OSWorld-derived task variants in which the original task remains achievable, but the environment is modified to introduce latent hazards such as destructive overwrites, etc. Each variant is paired with augmented evaluators that retain the original task-success criterion while adding explicit state-based safety invariants, allowing us to distinguish safe completions from unsafe completions that satisfy the nominal task objective. Our experimental results on OSGuard show that current multimodal guardrails can perform well on isolated action judgments, while risk-augmented execution exposes remaining gaps between local oversight and reliable end-to-end safety. This dual-granularity design enables more precise diagnosis of whether models can both recognize unsafe proposed actions and improve full-task safety when deployed as guardrails.

15.
arXiv (quant-ph) 2026-06-24

On the Limits of Stretching Quantum Pseudorandomness

arXiv:2606.24736v1 Announce Type: new Abstract: Pseudorandom states, introduced by Ji, Liu, and Song (CRYPTO '18), are quantum analogues of classical pseudorandom generators. A fundamental property of classical pseudorandom generators is that their output can be stretched to arbitrary polynomial length. Whether an analogous stretching property holds for quantum pseudorandom states remains unclear. In this work, we prove the first black-box separation between single-copy secure pseudorandom states ($\mathsf{1PRS}$) with different output lengths. Specifically, we construct a quantum oracle relative to which $\mathsf{1PRS}$ with output length $m(n)=1.1n$ exist, but $\mathsf{1PRS}$ with output length $m(n)=\Omega(n^{2+\epsilon})$ do not, for any $\epsilon>0$. Our proof leverages the Common Haar Random State (CHRS) model introduced by Chen, Coladangelo, and Sattath (EUROCRYPT '25), and introduces a technique to bound the effective number of resource CHRS states utilized by any $\mathsf{1PRS}$ generator in this model.

16.
arXiv (CS.AI) 2026-06-16

FOUNDv2: Learning Unified User Quantized Tokenizers for User Representation

arXiv:2508.00956v3 Announce Type: replace-cross Abstract: User representation learning serves as a fundamental pillar for personalized services on large-scale web platforms. Despite its importance, conventional continuous embedding methods face significant challenges, including the lack of a unified paradigm for multi-source data integration, prohibitive storage overhead due to low information density, and the lack of multi-scale modeling granularity. To overcome these limitations, we introduce FOUNDv2, a comprehensive user representation scheme centered on the Unified User Quantized Tokenizer U2QT) framework. FOUNDv2 transforms heterogeneous user data into a standardized discrete token space through a robust two-stage architecture. Specifically, the framework first extracts compact feature representations and subsequently employs a multi-view RQ-VAE to discretize them into storage-efficient tokens using shared and source-specific codebooks. To empower these representations with predictive intelligence, we further design multi-scale alignment objectives to capture both fine-grained behavioral dependencies and macro-temporal periodicity. Extensive experiments on various benchmarks demonstrate that FOUNDv2 consistently outperforms task-specific baselines while achieving substantial reductions in storage and computational costs. Finally, the large-scale deployment of FOUNDv2 on Alipay validates its practical scalability and efficiency across diverse industrial scenarios. The main code is available at: https://github.com/chuanhe1999/FOUNDv2.

17.
arXiv (CS.AI) 2026-06-24

Cycle-Consistent Neural Explanation of Formal Verification Certificates

arXiv:2606.24414v1 Announce Type: new Abstract: Formal verification produces machine-checkable certificates that attest to the satisfaction or violation of temporal properties, yet these certificates remain opaque to non-specialist stakeholders. We propose a cycle-consistent neural architecture that generates faithful natural language explanations of verification certificates. A forward network NN1 maps certificates to explanations, and an inverse network NN2 reconstructs certificates from explanations; a symbolic verifier closes the loop, providing a differentiable faithfulness proxy. A pointer-generator mechanism ensures lexical grounding by copying state names directly from the certificate. We evaluate on 420 test certificates spanning six verification methods (bounded proof, k-induction, inductive invariant, lasso, reachability, witness pair) in both YES and NO verdict variants, drawn from a financial compliance domain with 207 named states. Our trained architecture, combined with a hybrid inference-time routing strategy, achieves 90.0% cycle-verified soundness, surpassing a multi- LLM few-shot baseline (76.1% for the best of 16 LLM combinations across four frontier models) by 13.9 percentage points. The neural model wins on 10 of 12 verdict/kind categories, with three categories reaching 100% soundness. The architecture offers 860x faster inference (185 ms vs. 160 s per certificate for the full multi-LLM baseline), offline operation, deterministic outputs, and zero per-inference cost. These results demonstrate that trained specialization outperforms general-purpose LLM prompting for structured certificate explanation, while eliminating the deployment constraints of cloud-based inference.

18.
arXiv (CS.CV) 2026-06-18

Native Active Perception as Reasoning for Omni-Modal Understanding

Passive models for long video understanding typically rely on a "watch-it-all" paradigm, processing frames uniformly regardless of query difficulty, causing computational cost to grow with video duration. Although interactive frameworks have emerged, they often rely on global pre-scanning, and their context cost still scales with video length. We propose OmniAgent, the first native omni-modal agent that formulates video understanding as a POMDP-based iterative Observation-Thought-Action cycle. OmniAgent executes on-demand actions to selectively distill audio-visual cues into a persistent textual memory, effectively decoupling reasoning complexity from raw video duration. To operationalize this, we introduce (1) Agentic Supervised Fine-Tuning to bootstrap native active perception via best-of-N trajectory synthesis with dual-stage quality control, and (2) Agentic Reinforcement Learning with TAURA (Turn-aware Adaptive Uncertainty Rescaled Advantage), which leverages turn-level entropy to steer credit assignment toward pivotal discovery turns. Crucially, OmniAgent exhibits positive test-time scaling, where performance improves as the number of reasoning turns increases, validating the efficacy of active perception. Empirical results across ten benchmarks (e.g., VideoMME, LVBench) demonstrate that OmniAgent achieves state-of-the-art performance among open-source models. Notably, on LVBench, our 7B agent outperforms the 10$\times$ larger Qwen2.5-VL-72B (50.5% vs. 47.3%).

19.
arXiv (CS.LG) 2026-06-16

A Multimodal Approach to Alzheimer's Diagnosis: Geometric Insights from Cube Copying and Cognitive Assessments

arXiv:2512.16184v2 Announce Type: replace Abstract: Early and accessible detection of Alzheimer's disease (AD) remains a critical clinical challenge, and cube-copying tasks offer a simple yet informative assessment of visuospatial function. This work proposes a multimodal framework that converts hand-drawn cube sketches into graph-structured representations capturing geometric and topological properties, and integrates these features with demographic information and neuropsychological test (NPT) scores for AD classification. Cube drawings are modeled as graphs with node features encoding spatial coordinates, local graphlet-based topology, and angular geometry, which are processed using graph neural networks and fused with age, education, and NPT features in a late-fusion model. Experimental results show that graph-based representations provide a strong unimodal baseline and substantially outperform pixel-based convolutional models, while multimodal integration further improves balanced classification performance and discriminative ability. SHAP-based interpretability analysis identifies specific graphlet motifs associated with corner integrity and edge continuity as key predictors, closely aligning with clinical observations of distorted cube drawings in AD. Together, these findings establish graph-based analysis of cube-copying behavior as an interpretable, non-invasive, and scalable framework for Alzheimer's disease screening.

20.
arXiv (CS.CV) 2026-06-11

Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To address this challenge, we propose Adv-TGD, a generative adversarial attack framework that synthesizes photorealistic faces capable of impersonating target identities and deceiving face recognition systems. Built upon Stable Diffusion, Adv-TGD performs per-sample LoRA fine-tuning conditioned on concise textual prompts to generate natural yet adversarially manipulated identities. Unlike conventional identity-attack approaches, our method optimizes lightweight cross-attention adapters for each source-target pair within a single-step denoising process. Latent blending is constrained by a face-local heatmap mask to ensure spatially precise identity manipulation while preserving non-sensitive regions. We introduce a composite objective that integrates masked epsilon-MSE reconstruction, thresholded identity divergence in FR embedding space, directional feature alignment, and source-similarity suppression to balance adversarial attack and visual realism. Optionally, LLaVA-generated attribute prompts enhance fine-grained semantic details without reintroducing identity cues. Under the black-box evaluation protocol, Adv-TGD attains an average attack success rate (ASR) of 85.90% across IR152, IRSE50, MobileFace, and FaceNet, surpassing the semantic SOTA baseline Adv-CPG by +6.25 points, diffusion-based makeup method DiffAIM by +3 points, and noise-based P3-Mask by +16 points. Despite its strong attack efficacy, Adv-TGD preserves high visual fidelity (PSNR = 27.15 dB, SSIM = 0.981). Furthermore, we demonstrate the flexibility of our framework by successfully extending it to in-the-wild datasets (LADN), general object classification (ImageNet), and transformer-based diffusion models (FLUX.1).

21.
arXiv (CS.CL) 2026-06-12

A Unifying Lens on Reward Uncertainty in RLHF

Reinforcement learning from human feedback (RLHF) is bottlenecked by reward hacking, where the policy exploits errors in a proxy reward model (RM) and produces high RM scores without genuine quality gains. A natural mitigation is pessimism: lowering rewards in regions where the RM is uncertain. However, standard scalar RMs provide no principled notion of uncertainty. We argue that the right object is a distributional reward model $p(r\mid x,y)$. Under either a Bayesian inference or a KL-distributionally robust optimization (KL-DRO) lens, the KL-regularized RLHF objective admits a closed-form effective reward $\tilde r(x,y) = \pm\beta\log\mathbb{E}_p[e^{\pm r/\beta}]$. The pessimistic branch unifies the prior heuristics for RM ensemble aggregation: mean aggregation, worst-case optimization (WCO), and uncertainty-weighted optimization (UWO) all emerge as limits or truncations of this single expression. This also clarifies the implicit assumptions of each existing rule.

22.
Nature Medicine 2026-06-10

Dual-target gene therapy in Parkinson’s disease: a multicenter phase 1 trial

Authors:

Restoring striatal dopamine synthesis is a promising gene therapy strategy for Parkinson’s disease. Previous adeno-associated virus-mediated aromatic L-amino acid decarboxylase (AADC) monotherapies remain dependent on exogenous levodopa, whereas multigene delivery is constrained by strict adeno-associated virus packaging limits. A ‘dual approach’ targeting the two rate-limiting enzymes, tyrosine hydroxylase (TH) and AADC, offers the potential for autonomous dopamine synthesis. We report the 12-month primary safety and tolerability outcomes of a multicenter, open-label, dose-escalation, phase 1 trial evaluating BBM-P002, a new adeno-associated virus vector—AAVT42—codelivering constitutively active TH and AADC. Ten participants with moderate-to-advanced Parkinson’s disease were enrolled and received bilateral intraputaminal infusions across doses of 4.0 × 1011 vg (Cohort 1; n = 1), 6.0 × 1011 vg (Cohort 2; n = 2), 1.0 × 1012 vg (Cohort 3; n = 2) and 1.2 × 1012 vg (Cohort 4; n = 5). The trial achieved its primary outcome, as BBM-P002 demonstrated a favorable safety and tolerability profile within 12 months post-treatment. No dose-limiting toxicities or drug-related serious adverse events occurred. A total of 23 adverse events were reported, all judged unrelated to BBM-P002 and primarily mild and transient. Systemic toxicity and clinically meaningful immunogenicity were absent. In conclusion, intraputaminal delivery of BBM-P002 was safe and well tolerated in this phase 1 trial, supporting continued clinical development. ClinicalTrials.gov registration: NCT05822739 . Phase 1 results reveal that BBM-P002, a dual-target gene therapy co-delivering TH and DDC, is safe and well tolerated in Parkinson’s disease, with 12-month motor improvements signaling therapeutic potential.

24.
arXiv (quant-ph) 2026-06-16

Microscopic exceptional points in the post-selected open Jaynes–Cummings model

arXiv:2606.14982v1 Announce Type: new Abstract: Phenomenological non-Hermitian Hamiltonians track selected signatures of complex reservoir dynamics, while post-selected no-jump effective Hamiltonians derived from microscopic open-system theory reveal the underlying system–reservoir physics. We derive such a Hamiltonian for the open Jaynes–Cummings model using a Moore–Penrose normalized $\mathrm{su}(2)$ representation that removes the vacuum-sector singularity and diagonalizes the full Hamiltonian by one operator rotation. Starting from a zero-temperature bosonic reservoir, we obtain a Gorini–Kossakowski–Sudarshan–Lindblad master equation under the Born–Markov approximation with full Bohr-frequency resolution. We use partial Bohr-frequency resolution to build a consistent post-selected no-jump Hamiltonian near exceptional points, where decay rates become comparable to Rabi frequencies and remove the scale separation behind full resolution. The normalized $\mathrm{su}(2)$ form of the resulting non-Hermitian Jaynes–Cummings Hamiltonian reveals the effects of Lamb-shifted detuning, diagonal loss imbalance, and reservoir-modified coupling. Our microscopic exceptional-point analysis recovers the experimentally reported single-excitation exceptional point for unequal independent losses and identifies regimes absent from the standard phenomenological model; for example, equal correlated losses with orthogonal channel phase produce a second-order exceptional point at the same loss-to-coupling ratio in every excitation sector.

25.
arXiv (CS.AI) 2026-06-25

Training for the Model You Return: Improving Optimization for Iterate-Averaged Language Models

arXiv:2606.25086v1 Announce Type: cross Abstract: Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the final iterate itself. This raises a fundamental question: given that we will return an iterate average, how should we change training to improve the performance of this average? We study this question by formulating optimizer design for the iterate-average estimator as an optimal-control problem. In a continuous-time stochastic quadratic model, we solve for the control strategy that minimizes the error of the returned average subject to a penalty on the size of the intervention. A practical approximation to this controller yields PACE, a lightweight wrapper around AdamW that pulls the live weights toward their exponential moving average with a clipped, per-coordinate control strength. We prove that a stylized version of PACE converges at the standard stochastic convex optimization rate, up to a factor depending on the averaging rule, while in the quadratic setting it can strictly improve the limiting squared error of the iterate-average estimator and can do so by an arbitrarily large factor on some instances. Empirically, our results suggest that PACE improves over AdamW and EMA-evaluated AdamW in supervised fine-tuning of 1-2B parameter LMs and in GPT-2 pretraining on FineWeb for a wide range of learning rates, decay schedules, and other hyperparameters.