中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
bioRxiv (Bioinfo) 2026-06-19

ContinuumCellAgent: A Framework-Guided Agent for Long-Horizon Scientific Research

作者:
Li↗Lu↗Fang↗Xu↗

AI-scientist systems are beginning to automate parts of scientific research. We present ContinuumCellAgent, an autonomous agent that executes literature review, hypothesis formation, computational experimentation, manuscript drafting, and adversarial peer review as a single unattended run. Existing AI scientist systems remain difficult to diagnose because they lack modularity, systematic prompt grounding, and observability into long-running behavior. ContinuumCellAgent addresses these gaps with a modular supernode architecture for stage-wise backend swapping, protocols grounded in curated research-method checklists that also define reviewer rubrics, and a diagnostics layer that records file-based artifacts, message traces, and state transitions. We evaluate the system on open-domain QA benchmarks and biomedical/longevity case studies, showing that it can produce checkable research artifacts while exposing pipeline dynamics for rigorous AI co-scientist research.

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CL) 2026-06-11

Toward Preference-aligned Large Language Models via Residual-based Model Steering

作者:
Lucio La Cava↗Andrea Tagarelli↗

Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approaches such as Reinforcement Learning from Human Feedback or Direct Preference Optimization typically require curated data and expensive optimization over billions of parameters, and eventually lead to persistent task-specific models. In this work, we introduce Preference alignment of Large Language Models via Residual Steering (PaLRS), a training-free method that exploits preference signals encoded in the residual streams of LLMs. From as few as one hundred preference pairs, PaLRS extracts lightweight, plug-and-play steering vectors that can be applied at inference time to push models toward preferred behaviors. We evaluate PaLRS on various small-to-medium-scale open-source LLMs, showing that PaLRS-aligned models achieve consistent gains on mathematical reasoning and code generation benchmarks while preserving baseline general-purpose performance. Moreover, when compared to models aligned with DPO and SimPO, they perform better with great time-savings. Our findings highlight that PaLRS offers an effective, much more efficient and flexible alternative to standard preference optimization pipelines, offering a training-free, plug-and-play mechanism for alignment with minimal data.

阅读与讨论 → 访问原文 →
03.
arXiv (CS.CL) 2026-06-18

Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports

作者:
Qingyu Lu↗Ruochen Li↗Liang Ding↗Yufei Xia↗Youxiang Zhu↗Dacheng Tao↗

Reliable evaluation of generated radiology reports requires strict clinical accuracy, as omitted critical findings or mischaracterized radiographic observations can directly affect patient care. Existing metrics obscure this requirement by reducing report quality to a medically ungrounded scalar. Although Large Language Models (LLMs) possess rich medical knowledge, they likewise struggle to draw a reliable boundary between clinically significant errors and harmless variation. We study this boundary using ReEvalMed benchmark as testbed and evaluate metric-level clinical significance from detecting true clinical errors ("Discrimination") and tolerating insignificant variations ("Robustness"). Across 8 LLM evaluators under one-pass and two-pass settings, we identify a widespread discrimination bias: models effectively detect errors but also over-penalize harmless rephrasings. To mitigate this, we synthesize 4k report pairs and train lightweight interpretable metrics on Qwen3-8B and MedGemma-4B. Our trained metric sharpens the clinical significance boundary, surpassing 32B-scale medical LLMs and remaining competitive with proprietary models. Crucially, the more costly two-pass setting fails to consistently improve overall performance and mainly trades discrimination for robustness. These findings suggest one-pass trained metrics as the practical choice for cost-sensitive deployment, with two-pass inference reserved for settings where D-R balance is critical. We will release the dataset and metric.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.LG) 2026-06-11

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal

作者:
Leon Bergen↗Usha Bhalla↗Sidharth Baskaran↗Max Loeffler↗Raphael Sarfati↗Dhruvil Gala↗Ryan Panwar↗Santiago Aranguri↗Thomas Fel↗Atticus Geiger↗Matthew Kowal↗Siddharth Boppana↗…

arXiv:2606.12360v1 Announce Type: new Abstract: Language-model post-training is the main stage at which model behavior is shaped, yet it still largely involves optimization of scalar rewards that summarize diverse desiderata. This abstraction gives practitioners little visibility into what their data actually teaches models, allowing spurious correlations to be learned by a model and inducing undesirable behaviors such as over-stylization and sycophancy. To address this problem, we ask: can we inspect a preference dataset before optimization and decide, at the level of concepts, which behaviors a model should be allowed to learn? Motivated by this, we introduce a data-centric post-training pipeline that uses interpretability protocols to develop statistical hypotheses for the latent concepts separating preferred from dispreferred generations, making them explicit for fine-grained user feedback. Building on this view, we unify several interpretability-based training protocols as ways of shaping rewards via feature or data interventions. Empirically, we show that our pipeline diagnoses undesirable signals in existing preference data, mitigates off-target learning, and can also help amplify or shape desired properties such as safeguards and model personality. More broadly, our results suggest that interpretability can turn post-training from optimizing opaque proxy rewards into a process of auditing and sculpting the learning signal itself.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.LG) 2026-06-15

Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization

作者:
Na\"il B. Khelifa↗Richard E. Turner↗Ramji Venkataramanan↗

arXiv:2606.13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution. Existing theoretical works bound finite-round error accumulation in the context of diffusion models, but two questions remain open:~what distribution does the recursion converge to, and how fast? We answer both, isolating a mechanism distinct from imperfect learning: even with perfect score estimation and exact sampling, the early stopping of the reverse diffusion (required for numerical stability) drives a progressive drift away from the data distribution. We prove that this recursion converges geometrically to a unique limiting distribution, which admits a closed-form characterization as an infinite mixture of increasingly Gaussian-smoothed versions of the data distribution. A Hermite spectral decomposition of this limit reveals that recursive training acts as a low-pass filter: higher-order modes, which encode fine non-Gaussian structure, are attenuated much more strongly than coarse modes. This spectral picture motivates annealed truncation schedules that progressively shrink truncation times across retraining rounds; we prove that any schedule converging to $0$ asymptotically eliminates recursive compounding. Finally, we show our idealized characterization is robust: in the presence of discretization and score estimation errors, the learned distribution remains in a Wasserstein-2 ball around the ideal limit, with mode-dependent contraction rates that contract high-order errors faster than low-order ones. We validate the theory on synthetic Gaussian mixtures and CIFAR-10.

阅读与讨论 → 访问原文 →
06.
arXiv (math.PR) 2026-06-17

The Erdős-Hajnal High-Girth Subgraph Conjecture Holds in the Polynomial Chromatic-Sparsity Regime

作者:
Eric Li↗

arXiv:2606.17901v1 Announce Type: cross Abstract: For a graph $G$ put $h_r(G)=\max{\chi(H):H\subseteq G,\operatorname{girth}(H)\ge r}.$ Erdős and Hajnal asked whether $h_r(G)\to\infty$ as $\chi(G)\to\infty$, for every fixed $r\ge4$. We prove this in every fixed polynomial edge-density regime: for all $r\ge4$, $k\ge2$, $P,C>0$, there is $M=M_{r,k}(P,C)$ such that $\chi(G)\ge M,\ e(G)\le C\chi(G)^P\Longrightarrow h_r(G)\ge k.$ Quantitatively, after replacing $P$ by $P\vee2$ and $C$ by $C\vee2$, $M_{r,k}(P,C)\le \exp!\left(O_{r,k}\bigl((P+2+\log(C\vee2))^2\bigr)\right),$ and consequently the same conclusion holds throughout the quasi-polynomial range $e(G)\le \exp\bigl(C_0(\log\chi(G))^a\bigr),\ 1 < a < 3/2,$ for all sufficiently large $\chi(G)$. In each fixed polynomial-density regime we also obtain $f_{P,C}(k,r)\le k^{O_{r,P,C}(1)}.$ The proof combines a chromatic-defect random extraction lemma, compact and near-quadratic sparse-core bases, and a peeling/thinning bootstrap increasing the admissible edge exponent by $1/(r-1)$. We also prove structural saturation results for possible counterexamples, including Moore-strength exact-cycle packings and quadratic saturation in projected colour-pair space. Finally, writing $h_r^{\mathrm f}(G)=\max{\chi_{\mathrm f}(H):H\subseteq G,\operatorname{girth}(H)\ge r},$ we develop a fractional random-extraction framework based on Mohar-Wu preservation. We prove sufficient cheap-cycle-killing criteria and verify them for several structured families, including clique-organised families, line graphs of incidence graphs of equal-order generalized quadrangles and generalized hexagons, and the Bohman-Keevash tracking-time triangle-free-process graph. We also isolate a density-free obstruction that any proof using this fractional surgery route must overcome.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.LG) 2026-06-11

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling

作者:
Felipe Oviedo↗Fiodar Kazhamiaka↗Esha Choukse↗Allen Kim↗Amy Luers↗Melanie Nakagawa↗Ricardo Bianchini↗Juan M. Lavista Ferres↗

arXiv:2509.20241v2 Announce Type: replace Abstract: As AI inference scales to billions of queries, estimates of per-query energy use are increasingly important for capacity planning, efficiency interventions, and policy. Yet many public estimates assume non-production settings, leading to systematic overestimation. We introduce a bottom-up framework estimating inference energy from token throughput, node power, and overhead under large-scale deployment assumptions. For frontier-scale models (>200B parameters) on H100 nodes, we estimate a median energy of 0.31 Wh/query (IQR 0.16-0.60), indicating widely cited estimates are overstated by 4-20x. In test-time scaling scenarios 15x longer than typical queries, the median energy rises 13x to 3.91 Wh (IQR 2.15-7.05). Across models, serving systems, and hardware, we estimate 8-20x line-of-sight energy reductions. At datacenter scale, serving 1 billion queries/day requires 0.7 GWh; if 10% are long queries, demand rises to 1.7 GWh/day. With efficiency interventions, it falls to 0.8 GWh/day, mitigating the energy impact of test-time scaling.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.CL) 2026-06-16

Understanding LLM Reasoning for Abstractive Summarization

作者:
Haohan Yuan↗Haopeng Zhang↗

Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, evaluating both summary quality and factual faithfulness. Our results show that reasoning is not a universal solution and its effectiveness depends strongly on the strategy and the summarization setting. In particular, we find a trade-off between summary quality and factual faithfulness. Explicit reasoning strategies often improve reference-based quality, but may weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. We further find that increasing an LRM's internal reasoning budget does not reliably improve summarization and can even reduce factual consistency. These findings suggest that, for summarization, more reasoning is not always better. Effective reasoning should preserve faithful compression rather than induce over-elaboration. Our source code is publicly available.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-16

Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems

作者:
Yi Xie↗Jiawei Du↗Yu Cheng↗Jiuan Zhou↗Zhaoxia Yin↗

arXiv:2606.15242v1 Announce Type: cross Abstract: Skills are becoming the capability layer through which LLM agents turn plans into actions, but their use introduces security risks such as data leakage, unauthorized operations, and tool misuse. Existing vetting usually evaluates each skill in isolation, while real agent tasks often invoke multiple skills in a shared execution context. This creates Skill Composition Risk (SCR): a skill that appears benign alone can become harmful when its outputs, trust signals, authorization cues, or side effects influence later invocations along an activated path. We introduce SCR-Bench to evaluate this risk in controlled, sandboxed skill environments. Rather than relying only on textual intent or surface behavior, SCR-Bench records downstream state changes and path-level outcomes across composed skill executions. It contains three sub-benchmarks: SCR-CapFlow for capability-flow composition, SCR-TrustLift for trust-transfer composition, and SCR-AuthBlur for authorization-confusion composition. Across SCR-Bench, composed paths expose risks that are largely absent under isolated evaluation. In SCR-CapFlow, attack success rate reaches 33.6 percent under composition, compared with near-zero isolated baselines. In SCR-TrustLift, attack success rate exceeds 96.5 percent on four of five backends. In SCR-AuthBlur, the risky-approval rate increases by 71.8 percent relative to the L0 isolated baseline under the L1 context setting. These results show that agent skill security should be assessed at the level of activated paths rather than isolated artifacts. SCR and SCR-Bench provide a foundation for path-aware risk evaluation and defense in LLM agent skill ecosystems. Benchmark: https://github.com/saint-viperx/SCR_Bench.

阅读与讨论 → 访问原文 →
10.
arXiv (quant-ph) 2026-06-16

A short proof of the modified Kretschmann-Schlingemann-Werner conjecture

作者:
Satvik Singh↗

arXiv:2606.16418v1 Announce Type: new Abstract: Let $\Phi_1, \Phi_2 : \mathbb{M}_d(\mathbb{C})\to \mathbb{M}_n(\mathbb{C})$ be two quantum channels with respective Stinespring isometries $V_1, V_2 : \mathbb{C}^{d}\to \mathbb{C}^{n} \otimes \mathbb{C}^{m}$ on any common dilation space $\mathbb{C}^{m}$. We prove that there exists a unitary $U$ on $\mathbb{C}^{m}$ such that $\|V_1-({\bf1}\otimes U)V_2\|_\infty\leq\sqrt{2\|\Phi_1-\Phi_2\|_\diamond},$ thus resolving vom Ende's modification of the Kretschmann-Schlingemann-Werner conjecture in the affirmative.

阅读与讨论 → 访问原文 →
11.
bioRxiv (Bioinfo) 2026-06-21

Machine learning evaluation of gene expression-based ALS subtypes across brain and blood tissues

作者:
Gomez↗E. A↗Al Khleifat↗Troakes↗Al-Chalabi↗Iacoangeli↗

The clinical and molecular heterogeneity observed in amyotrophic lateral sclerosis (ALS) presents a challenge for diagnosis, prognosis, and treatment. RNA sequencing of post-mortem brain samples from ALS patients has identified several subtypes with distinct molecular signatures. We sought to evaluate these subtypes across diverse tissues and datasets and assess the feasibility of supervised machine learning models for sample classification. Unsupervised clustering and pathway analysis were performed to confirm the presence of ALS subtypes in motor cortex samples. Three machine learning strategies were then used to create models based on post-mortem motor cortex expression data of 112 people with ALS from the London Neurodegenerative Diseases Brain Bank. These models were subsequently improved through feature selection and evaluated in independent cohorts from motor cortex (n = 257, NYGC ALS Consortium) and blood (n = 96, Macquarie University Neurodegenerative Disease Biobank) samples. Multi-class linear discriminant analysis (LDA) models were then used for subtype classification. Clustering of ALS post-mortem motor cortex samples confirmed the presence of three subtypes: neuroinflammation (ALS-Neu), extracellular matrix organisation and muscle contraction (ALS-OxA), and synaptic and neuropeptide signalling (ALS-SNs). Among all machine learning strategies, random forests produced the most accurate and stable models for binary classification (~93% accuracy across the three subtypes). After feature selection, random forest models were able to classify samples from an independent post-mortem motor cortex cohort in their respective subtypes (AUC of ~0.98 across the three subtypes). When these models were evaluated in blood using LDA, we found consistent clustering patterns, with samples aligning in the same subtype regions of the post-mortem motor cortex samples, with ALS-SNs being the subtype in which samples were classified with the highest confidence (LDA class probability ~86%). Moreover, classification for this subtype improved when blood samples were collected closer to death. Our findings support the presence of three gene expression-based ALS subtypes in motor cortex samples and the utility of machine learning strategies for subtype classification. We also observed that the subtypes identified in the brain partially match those in the blood, with samples from the late stages of the disease more likely to be correctly predicted into the ALS-SNs cluster. This suggests a longitudinal effect in subtype identification that requires further investigation.

阅读与讨论 → 访问原文 →
12.
arXiv (CS.AI) 2026-06-16

AQ4SViT: An Automated Quantization Framework with Search Gating Policy for Compressing Spiking Vision Transformers

作者:
Rachmad Vidya Wicaksana Putra↗Saad Iftikhar↗Muhammad Shafique↗

arXiv:2606.15523v1 Announce Type: cross Abstract: Spiking Vision Transformers (SViTs) have emerged as alternative low-power ViT models, but their large sizes hinder their deployments on resource-constrained embedded AI systems. To address this, state-of-the-art works proposed quantization techniques to compress SViT models, but their manual, human-guided approach needs a huge design time and power/energy consumption to find the appropriate quantization setting for each given network, making this approach not scalable for quantizing multiple networks. Toward this, we propose AQ4SViT, a novel automated quantization framework for SViTs that can provide quick quantization settings with good trade-offs between accuracy and memory. To achieve this, AQ4SViT employs the following key ideas: quantization search strategy that evaluates the quantization setting candidates while considering the accuracy constraint; and search gating policy that quickly evaluates and selects promising quantization candidates by leveraging membrane potential drift as a performance proxy. In the search gating policy, AQSViT employs two search algorithm variants to provide trade-off options: Greedy search, which performs fast but may lead to local optima; and Beam search, which performs slower but has better performance in finding global optima selection due to a wider search space. Experimental results show that AQ4SViT-Greedy quickly finds the appropriate quantization settings, achieving up to 6.6x faster search time and up to 82.5% memory saving compared to the state-of-the-art; while AQ4SViT-Beam further reduces the memory footprint by up to 90% compared to the state-of-the-art, but with 4.5x longer search time; all these results are obtained while maintaining high accuracy within 1.5% from the original/non-quantized models on the ImageNet dataset. These results highlight that AQ4SViT framework offers advancements toward SViT deployments on embedded AI systems.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.LG) 2026-06-12

Prediction-Powered Causal Inference by Automatic Debiased Machine Learning and Semi-Supervised Riesz Regression

作者:
Masahiro Kato↗

arXiv:2606.12892v1 Announce Type: cross Abstract: This study investigates semiparametric efficient estimation of causal and structural parameters in a semi-supervised setting. In our setting, unlabeled auxiliary regressors are available in addition to labeled observations consisting of outcomes and regressors. Our goal is to construct estimators of causal and structural parameters whose asymptotic variances are smaller than those of estimators constructed using only labeled data. We refer to this framework as prediction-powered causal inference (PPCI). We first derive the efficient influence function and the efficiency bound, which imply that the use of auxiliary regressors can attain a smaller asymptotic variance than the efficiency bound attainable from labeled observations alone. Then, by combining the efficient influence function with the debiased machine learning (DML) framework, we propose methods that we call DML-PPCI. If we construct an estimating-equation estimator, we refer to the method as EE-DML-PPCI; if we construct a targeted-learning estimator, we refer to the method as TMLE-DML-PPCI. The asymptotic variances of both estimators match our derived efficiency bound. In the construction of the estimators, estimation of the efficient influence function plays an important role. In our study, the efficient influence function is also a Neyman orthogonal score, which depends on the Riesz representer and the regression function. For Riesz representer estimation, we develop semi-supervised generalized Riesz regression with convergence rate guarantees.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.CL) 2026-06-18

As Easy as Rocket Science: Assessing the Ability of Large Language Models to Interpret Negation in Figurative Language

作者:
Jasmine Owers↗Edwin Simpson↗Martha Lewis↗

Figurative language and negation are two areas that challenge current language models, however, both are widely used throughout written and spoken language. Large language models (LLMs) are also widely used in everyday contexts where they cannot necessarily be tuned for a specific dataset. It is therefore essential to understand the ability of LLMs to correctly interpret text that includes both negation and figurative language. To investigate this, we develop a set of new annotations to an existing dataset of figurative language, and test a range of language models on the dataset. We find that the combination of negation and figurativeness can present a particular challenge, and that performance overall and across different negation types is particularly dependent on the prompt style used.

阅读与讨论 → 访问原文 →
15.
arXiv (CS.CV) 2026-06-11

Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment

作者:
Jia Li↗Qian Chen↗Wei Wang↗Xinyu Li↗Zhenzhen Hu↗Dongsheng Shao↗Richang Hong↗Meng Wang↗

Personality assessment aims to infer stable personality traits from dynamic behaviors across language, voice, and facial cues. Since different personality dimensions are revealed through distinct behavioral perspectives, modeling trait-specific evidence is challenging. However, most existing approaches adopt a uniform multimodal fusion strategy across all dimensions, assuming identical modality contributions. This overlooks trait-specific modality preferences and introduces cross-modal interference. To address this issue, we propose a novel personality assessment framework called Traits Run Deeper, which consists of three components. Specifically, the Multimodal Foundation Representation (MFR) module constructs personality-oriented multimodal inputs and leverages psychology-informed semantic templates as anchors, enabling foundation models to capture trait-relevant information. Building upon MFR, the Trait-Specific Modality Fusion (TSMF) module acts as an asymmetric fusion mechanism, allowing each dimension to selectively exploit different modality pathways from modality-specific modeling to complementary fusion. Thus, TSMF captures heterogeneous modality preferences while reducing cross-modal contamination. Furthermore, the Distribution-Calibrated Personality Regression (DCPR) module mitigates label imbalance and central tendency bias through target distribution calibration, improving robustness and stability. Experimental results on the AVI Challenge 2026 validation set demonstrate the effectiveness of the proposed framework, reducing mean squared error (MSE) by approximately 25% compared with the baseline. Consistent improvements are observed on the official test set, where our method achieves the best performance and ranks first in the Personality Assessment Track. The source code will be made available at https://github.com/MSA-LMC/AVI2026.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.AI) 2026-06-18

User as Engram: Internalizing Per-User Memory as Local Parametric Edits

作者:
Bojie Li↗

arXiv:2606.19172v1 Announce Type: new Abstract: Personal memory in a language model is two problems: content and reasoning skill. The brain keeps the two apart (a sparse, local engram in the hippocampus for each episode, a slow neocortex for the shared skills that interpret it), so a new fact need not overwrite everything else. Most personalization today keeps a user's facts outside the weights, in a natural-language memory file or a retrieval index. When facts are written into the model instead, the standard recipe is the per-user LoRA adapter, which does the opposite of the brain, folding content and skill into one global weight delta. Writing a user's facts as a LoRA contaminates text unrelated to them; writing the same facts as local Engram rows leaves it mathematically untouched, resulting in a roughly 33,000x smaller memory footprint. We therefore propose User as Engram: store a user's content as surgical edits to the hash-keyed memory table of an Engram model, and carry the reasoning skill in one shared adapter. This layered design matches per-user LoRA's direct recall while delivering 5.6x higher indirect-reasoning accuracy on average, and never makes a single user worse at reasoning than the untouched base. The edit is a glass box: writing a fact switches on its lookup at exactly the trigger, adds the value the answer needs, leaves every other position unchanged to the last bit, and fails if written into the wrong layer. Because different users' facts land in disjoint hash slots, their edits compose: many users live in one shared table at once, stacking additively and losslessly, where a per-user LoRA, a single global weight delta, admits only one. Upon retrieval, a per-user Engram table does not grow with the population the retriever must search, so past ~100 facts it overtakes a retrieval pipeline on a 2.5x larger model.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.AI) 2026-06-17

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

作者:
Keane Ong↗Sabri Boughorbel↗Luwei Xiao↗Chanakya Ekbote↗Wei Dai↗Ao Qu↗Jingyao Wu↗Rui Mao↗Ehsan Hoque↗Erik Cambria↗Gianmarco Mengaldo↗Paul Pu Liang↗…

arXiv:2602.10635v3 Announce Type: replace Abstract: Socially intelligent AI systems must reason across diverse human behavioral tasks and generalize to new social contexts. However, behavioral data is inherently heterogeneous, comprising diverse modalities and prediction targets that produce uneven training signals across samples, creating imbalanced learning dynamics that challenge existing AI models. To address this, we develop Omnisapiens-7B 2.0, a foundation model for social behavior processing that explicitly addresses learning from heterogeneous behavioral data. This is enabled through Heterogeneity-Aware Relative Policy Optimization, a new RL method that rebalances learning signals across samples by approximating each sample's contribution to the policy update and using these estimates to drive geometrically centered, inertially smoothed advantage modulation for stable training. Omnisapiens-7B 2.0 achieves the best and most consistent performance across 10 behavioral tasks, while also attaining the best performance on all five held-out benchmarks, with gains of up to +12.02% and +9.37% respectively. Furthermore, it demonstrates more consistent and interpretable reasoning traces, supporting reliable real-world behavioral applications. Our model is available at https://github.com/MIT-MI/human_behavior_atlas.

阅读与讨论 → 访问原文 →
18.
arXiv (math.PR) 2026-06-17

Optional Stopping for Superhedging Supermartingales

作者:
Christian Bender↗Sebastian E. Ferrando↗

arXiv:2606.17452v1 Announce Type: new Abstract: Superhedging supermartingales, introduced by the authors in previous work, are non-probabilistic processes defined via subadditive outer integrals that carry a purely financial interpretation in terms of superhedging cost. Building on the Leinert-König theory of non-lattice integration, the present paper establishes several results that are classical in probability theory but whose non-probabilistic proofs require fundamentally new arguments: (i) a tower inequality for the conditional outer integral \overline{\sigma}_j applied at stopping times, reducing to equality when the integrand is conditionally integrable; (ii) three versions of Doob's optional stopping theorem, organised by the class of supermartingale and the range of the stopping times; and (iii) Dubins' upcrossing inequality in both finite- and infinite-time horizons. A key structural result, property (K)-a.e., identifies conditions under which the two superhedging operators \overline{\sigma}_j and \overline{I}_j coincide on non-negative functions, extending the scope of all preceding results to the positive operator \overline{I}_j. None of the proofs invoke classical measure-theoretic tools; in particular, (classical) integrability and measurability are not assumed. The analogues of classical stochastic results acquire a purely financial interpretation and, in this way, gain depth and generality by providing a context that is independent of any a priori probabilistic structure.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.LG) 2026-06-16

Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes

作者:
Tongyan Fang↗Siyuan Huang↗Naiyu Fang↗Ganlong Zhao↗Zhongjin Luo↗Jianbo Liu↗Xiaogang Wang↗Ying Dong↗Hongsheng Li↗

arXiv:2606.17043v1 Announce Type: cross Abstract: When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First, a single scalar signal conflates the two objectives of viability and efficiency; once basic success is achieved, the binary label provides no gradient to distinguish efficient completions from slow ones. Second, real-world rollouts mix autonomous and intervention segments; naively assigning episode outcomes across these boundaries introduces incorrect credit assignment. To address these issues, we propose Hierarchical Advantage-Weighted Behavior Cloning (HABC), which trains separate critic heads for these two objectives on different data subsets and combines their outputs with a state-adaptive balance. A state-adaptive gate $g_t$ merges their one-step advantages, prioritizing viability when success is uncertain and shifting to efficiency only when viability is high, and converts the result into per-transition weights on the actor loss. Intervention-aware credit assignment further restricts outcome labels to segments executed by the current policy, preventing supervision from leaking across intervention boundaries. In real-robot experiments on three contact-rich bimanual tasks, HABC raises success from supervised fine-tuning (SFT) baselines of 36%, 44%, and 12% to 92%, 88%, and 38%.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.AI) 2026-06-15

Beyond LoRA: Is Sparsity-Induced Adaptation Better?

作者:
Elijah Cadenhead↗Cristian McGee↗Xin Li↗El Houcine Bergou↗Aritra Dutta↗

arXiv:2606.13767v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) and its variants provide a memory- and compute-efficient alternative to full fine-tuning of pre-trained models. However, questions remain about the comparative generalizability of these approaches and how the structural restrictions on low-rank updates preserve effective adaptation performance. We present a historical framing, covering the past (full fine-tuning and original LoRA), the present (different variants of LoRA), and propose simpler, cheaper, parameter-efficient extensions by inducing sparsity within existing LoRA variants: Cheap LoRA (cLA), training a single low-rank factor with the other fixed (deterministically or, in its randomized variant, stochastically), and the chained circulant variant, ${c}^3$LA. We frame cLA as a structured instance of asymmetric LoRA, serving as a controlled column-subspace restriction of full fine-tuning. We derive information-theoretic generalization error bounds for these variants, marking one of the first endeavors in this area. Empirically, we evaluate 11 fine-tuning methods across 10 pre-trained models and 14 datasets, analyzing the fine-tuned models' performance and generalization using tools such as loss landscapes and spectral analysis. Despite the sensitivity of fine-tuned models to the pre-trained model, datasets, and other factors, our study suggests that restricting LoRA-based PEFT methods' adaptation to a sparse, structured column space remains competitive across tasks with their parameter-matched baselines while reducing up to 10% training time and peak GPU memory up to 15%, even with a naïve, non-optimized, sparse implementation. Our theoretical and empirical generalization measures provide a more consistent and principled approach to their cost-effective adaptation than commonly used analytical tools. Overview and code are available at: https://elicaden.github.io/Beyond_LoRA/.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.CL) 2026-06-11

A Resource for Enthymeme Detection in Controversial Political Discourse

作者:
Martial Pastor↗Nelleke Oostdijk↗

Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective. We present a resource of 1,482 tweets from politically controversial discourse, annotated by five annotators for the presence of enthymemes and their argument structure, designed to study label variation. We first revisit the definition of enthymemes and propose annotation guidelines anchored in Walton's argumentation schemes, offering a structured and constrained approach that nonetheless preserves room for the interpretive nature of the task. This contrasts with past resources, which tend to eliminate disagreement, obscuring its sources and preventing investigation of its potential benefits for model performance. We further propose a complexity analysis of the task, identifying where annotation imposes high cognitive load and may give rise to inconsistent annotation. Our preliminary experiments show that models trained on annotator disagreement outperform models trained on hard majority-vote labels. We close by reflecting on how structural openness in enthymeme definitions and guidelines enables the study of variation in subjective inferential processes for future resources and downstream NLP applications concerned with human inference.

阅读与讨论 → 访问原文 →
22.
arXiv (CS.CL) 2026-06-12

Structuring The Future: Diffusion LLM Speculative Decoding via Calibrated Draft Graphs

作者:
Sudhanshu Agrawal↗Risheek Garrepalli↗Raghavv Goel↗Christopher Lott↗Fatih Porikli↗Mingu Lee↗

Diffusion LLMs (dLLMs) have recently emerged as a powerful alternative to autoregressive LLMs (AR-LLMs) with the potential to operate at significantly higher token-generation rates. To unlock this potential, we present Spiffy, a speculative decoding algorithm to accelerate dLLM inference while provably preserving the model's output distribution. This work addresses the unique challenges involved in applying ideas from speculative decoding of AR-LLMs to dLLMs. Spiffy performs auto-speculation to eliminate the overheads of an independent draft model, structuring draft states in the form of a novel directed draft graph to take advantage of the bidirectional, blockwise nature of dLLM generation. These draft graphs are calibrated offline to maximize acceptance rates and are dynamically pruned during inference for improved computational efficiency. We present a detailed formulation of Spiffy and demonstrate its ability to accelerate LLaDA, Dream, and SDAR models in combination with KV caching and threshold-based dynamic unmasking leading to up to $8.6\times$ reduction in model inferences and $6.3\times$ acceleration in token rate.

阅读与讨论 → 访问原文 →
23.
PLOS Medicine 2026-05-08

Optimal minimal residual disease threshold in pediatric acute myeloid leukemia: A retrospective cohort study based on the TARGET database

作者:
Xiong-yu Liao↗

by Xiong-yu Liao, Hong Zheng, Jian-pei Fang, Dun-hua Zhou, Kun-yin Qiu Background Minimal residual disease (MRD) monitoring is a cornerstone of risk stratification in pediatric acute myeloid leukemia (AML), with a threshold of 0.1% conventionally defining positivity by flow cytometry. Advances in flow cytometric technologies, enabling detection of leukemic cells with higher sensitivity and specificity, warrant a reevaluation of whether a lower threshold improves prognostic accuracy. Methods and findings We conducted a retrospective cohort study using data from the Therapeutically Applicable Research to Generate Effective Treatments (TARGET)-AML initiative. The study population comprised 1,205 pediatric patients with de novo AML treated across Children’s Oncology Group (COG) clinical trial centers. Patients were enrolled between September 1996 and December 2016, with a median follow-up of 6.2 years (range: 0.5–20.1 years). The primary objective was to compare the prognostic performance of the traditional MRD threshold (≥0.1%) with a lower threshold (≥0.05%) after induction courses 1 and 2. The main outcome measure was 5-year event-free survival (EFS). Analyses included Kaplan−Meier survival estimates, Cox proportional hazards models to calculate hazard ratios (HR) with 95% confidence intervals (CI), receiver operating characteristic (ROC) curves, and net reclassification improvement (NRI). The optimal threshold for predicting 5-year EFS, determined by ROC analysis, was 0.05% after both induction course 1 (AUC: 0.840, 95%CI[0.76,0.88]) and course 2 (AUC: 0.854, 95%CI[0.78,0.89]). The 0.05% threshold demonstrated higher HR for the first event than the 0.1% threshold (after course 1: HR = 2.8, 95%CI[2.3,3.3]; P 

阅读与讨论 → 访问原文 →
24.
arXiv (CS.AI) 2026-06-16

Thinking with Visual Grounding

作者:
Junkai Zhang↗Yihe Deng↗Kai-Wei Chang↗Wei Wang↗

arXiv:2606.16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence. While recent vision-language models (VLMs) can produce natural-language reasoning traces, these traces often leave the supporting image regions implicit, making them hard to verify and difficult to supervise. We introduce visually grounded thinking, a reasoning process in which models interleave natural-language thoughts with explicit point or box groundings of the visual evidence used at each step. This lets the model express intermediate reasoning in language while grounding key objects in the image regions they refer to. To train this behavior, we construct a scalable synthesis pipeline that distills correct visual reasoning traces, extracts the visual objects required by the traces, grounds them with a SAM3-based agent, and derives aligned point and box supervision from the resulting masks. We further propose grounding-aware reinforcement learning, which combines answer correctness rewards with dense grounding rewards that score whether generated object references match the correct image evidence. Across two counting benchmarks and four spatial reasoning benchmarks, adding visually grounded thinking to Gemma3-4B-IT consistently improves performance over the original model and the non-grounded thinking baseline. On spatial reasoning, the visually grounded thinking 4B models match, and in some cases surpass, Gemma3-27B-IT from the same model family. Our analysis shows that point grounding is well suited to counting, while box grounding benefits most from explicit grounding rewards on spatial tasks. Overall, our results show that VLMs think better when their intermediate thoughts are tied to the image regions that make them true.

阅读与讨论 → 访问原文 →
25.
arXiv (CS.LG) 2026-06-12

PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models

作者:
Emma Kasteleyn↗Timo Maier↗Axel Lauer↗Veronika Eyring↗Pierre Gentine↗Ana Lucic↗

arXiv:2606.10642v2 Announce Type: replace Abstract: Machine learning weather prediction (MLWP) models have achieved impressive forecasting performance at a small fraction of the computational costs required for traditional physics-based methods. However, they are primarily (1) data-driven and (2) evaluated using pixel-wide error metrics (e.g., RMSE), so there are no guarantees that their forecasts are consistent with known physical laws. We introduce PhysMetrics$.$Weather, an evaluation framework that assesses the physical realism of MLWP models across three types of metrics: conservation, spectral, and dynamical. By quantifying physical realism, this tool guides the development of physics-informed architectures and helps evaluate whether MLWP models are reliable for operational use. Our framework is available on Github at https://github.com/Emmakast/PhysMetrics.Weather.

阅读与讨论 → 访问原文 →