# Research Papers — 2026-04 · bundle page 72 of 233

> Full-text markdown of papers #3551–3600 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-04/page/72
[← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/71.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-04/page/73.md)

### Multi-modal Test-time Adaptation via Adaptive Probabilistic Gaussian Calibration

Authors: Jinglin Xu, Yi Li, Chuxiong Sun, Xiao Xu, Jiangmeng Li, Fanjiang Xu
Published: 2026-04-21
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2604.19093v1

Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled target data during inference. Despite the documented success, the advancement of multi-modal TTA methodologies has been impeded by a persistent limitation, i.e., the lack of explicit modeling of category-conditional distributions, which is crucial for yielding accurate predictions and reliable decision boundaries. Canonical Gaussian discriminant analysis (GDA) provides a vanilla modeling of category-conditional distributions and achieves moderate advancement in uni-modal contexts. However, in multi-modal TTA scenario, the inherent modality distribution asymmetry undermines the effectiveness of modeling the category-conditional distribution via the canonical GDA. To this end, we introduce a tailored probabilistic Gaussian model for multi-modal TTA to explicitly model the category-conditional distributions, and further propose an adaptive contrastive asymmetry rectification technique to counteract the adverse effects arising from modality asymmetry, thereby deriving calibrated predictions and reliable decision boundaries. Extensive experiments across diverse benchmarks demonstrate that our method achieves state-of-the-art performance under a wide range of distribution shifts. The code is available at https://github.com/XuJinglinn/AdaPGC.

---

### RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation

Authors: Feng Jiang, Yang Chen, Kyle Xu, Yuchen Liu, Haifeng Wang, Zhenhao Shen, Jasper Lu, Shengze Huang, Yuanfei Wang, Chen Xie, Ruihai Wu
Published: 2026-04-21
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2604.19092v2

Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of using generated videos as scalable supervision for robot learning. However, for embodied manipulation, perceptual realism alone is not sufficient: generated interactions must also be physically consistent and executable by robotic agents. Existing benchmarks provide valuable assessments of visual quality and physical plausibility, but they do not systematically evaluate whether predicted behaviors can be translated into executable actions that complete manipulation tasks. We introduce RoboWM-Bench, a manipulation-centric benchmark for embodiment-grounded evaluation of video world models. RoboWM-Bench converts generated human-hand and robotic manipulation videos into embodied action sequences and validates them through execution in physically grounded simulation environments. Built on real-to-sim scene reconstruction and diverse manipulation tasks, RoboWM-Bench enables standardized, reproducible, and scalable evaluation of physical executability. Using RoboWM-Bench, we evaluate state-of-the-art video world models and observe that visual plausibility and embodied executability are not always aligned. Our analysis highlights several recurring factors that affect execution performance, including spatial reasoning, contact prediction, and non-physical geometric distortions, particularly in complex and long-horizon interactions. These findings provide a more fine-grained view of current model capabilities and underscore the value of embodiment-aware evaluation for guiding physically grounded world modeling in robotic manipulation.

---

### Fast estimation of Gaussian mixture components via centering and singular value thresholding

Authors: Huan Qing
Published: 2026-04-21
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2604.19091v1

Estimating the number of components is a fundamental challenge in unsupervised learning, particularly when dealing with high-dimensional data with many components or severely imbalanced component sizes. This paper addresses this challenge for classical Gaussian mixture models. The proposed estimator is simple: center the data, compute the singular values of the centered matrix, and count those above a threshold. No iterative fitting, no likelihood calculation, and no prior knowledge of the number of components are required. We prove that, under a mild separation condition on the component centers, the estimator consistently recovers the true number of components. The result holds in high-dimensional settings where the dimension can be much larger than the sample size. It also holds when the number of components grows to the smaller of the dimension and the sample size, even under severe imbalance among component sizes. Computationally, the method is extremely fast: for example, it processes ten million samples in one hundred dimensions within one minute. Extensive experimental studies confirm its accuracy in challenging settings such as high dimensionality, many components, and severe class imbalance.

---

### Towards Scalable Lifelong Knowledge Editing with Selective Knowledge Suppression

Authors: Dahyun Jung, Jaewook Lee, Heuiseok Lim
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.19089v1

Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model's original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.

---

### OLLM: Options-based Large Language Models

Authors: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.19087v1

We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a \textit{set of learned options} for the next token, indexed by a discrete latent variable. Instead of relying on temperature or sampling heuristics to induce diversity, OLLM models variation explicitly: a small latent space parametrizes multiple plausible next-token options which can be selected or searched by a downstream policy. Architecturally, OLLM is a lightweight "plug-in" that inserts two layers: an encoder and a decoder, before the output head, allowing almost any pretrained LLM to be converted with minimal additional parameters. We apply OLLM to a 1.7B-parameter backbone (only $1.56\%$ of parameters trainable) trained on OpenMathReasoning and evaluated on OmniMath. The SOTA LoRA-adapted baselines peak at $51\%$ final answer correctness, while OLLM's option set allows up to $\sim 70\%$ under optimal latent selection. We then train a compact policy in the latent space that emits latents to control generation. Operating in a low-dimensional option space makes reward optimization far more sample-efficient and substantially reduces common misalignments (e.g., language switching or degenerate reasoning), as the policy is constrained to options learned during SFT. Crucially, this alignment arises from model structure rather than additional KL or handcrafted alignment losses. Our results demonstrate that optionized next-token modeling enhances controllability, robustness, and efficiency in math reasoning, and highlight latent-space policy learning as a promising direction for reinforcement learning in LLMs.

---

### ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Authors: Kun Wang, Cheng Qian, Miao Yu, Lilan Peng, Liang Lin, Jiaming Zhang, Tianyu Zhang, Yu Cheng, Yang Wang
Published: 2026-04-21
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2604.19083v1

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the feasibility of backdoors in MLLMs via fine-tuning data poisoning to manipulate inference, the underlying mechanisms of backdoor attacks remain opaque, complicating the understanding and mitigation. To bridge this gap, we propose ProjLens, an interpretability framework designed to demystify MLLMs backdoors. We first establish that normal downstream task alignment--even when restricted to projector fine--tuning--introduces vulnerability to backdoor injection, whose activation mechanism is different from that observed in text-only LLMs. Through extensive experiments across four backdoor variants, we uncover:(1) Low-Rank Structure: Backdoor injection updates appear overall full-rank and lack dedicated ``trigger neurons'', but the backdoor-critical parameters are encoded within a low-rank subspace of the projector;(2) Activation Mechanism: Both clean and poisoned embedding undergoes a semantic shift toward a shared direction aligned with the backdoor target, but the shifting magnitude scales linearly with the input norm, resulting in the distinct backdoor activation on poisoned samples. Our code is available at: https://anonymous.4open.science/r/ProjLens-8FD7

---

### Reducing the Offline-Streaming Gap for Unified ASR Transducer with Consistency Regularization

Authors: Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Nune Tadevosyan, Vitaly Lavrukhin, Boris Ginsburg
Published: 2026-04-21
Categories: eess.AS, cs.AI, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2604.19079v1

Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified ASR framework for Transducer (RNNT) training that supports both offline and streaming decoding within a single model, using chunk-limited attention with right context and dynamic chunked convolutions. To further close the gap between offline and streaming performance, we introduce an efficient Triton implementation of mode-consistency regularization for RNNT (MCR-RNNT), which encourages agreement across training modes. Experiments show that the proposed approach improves streaming accuracy at low latency while preserving offline performance and scaling to larger model sizes and training datasets. The proposed Unified ASR framework and the English model checkpoint are open-sourced.

---

### S2MAM: Semi-supervised Meta Additive Model for Robust Estimation and Variable Selection

Authors: Xuelin Zhang, Hong Chen, Yingjie Wang, Tieliang Gong, Bin Gu
Published: 2026-04-21
Categories: cs.LG, cs.AI, stat.ML
arXiv: https://arxiv.org/abs/2604.19072v3

Semi-supervised learning with manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the key requirement is that the support of the unknown marginal distribution has the geometric structure of a Riemannian manifold. Typically, the Laplace-Beltrami operator-based manifold regularization can be approximated empirically by the Laplacian regularization associated with the entire training data and its corresponding graph Laplacian matrix. However, the graph Laplacian matrix depends heavily on the prespecified similarity metric and may lead to inappropriate penalties when dealing with redundant or noisy input variables. To address the above issues, this paper proposes a new Semi-Supervised Meta Additive Model (S$^2$MAM) based on a bilevel optimization scheme that automatically identifies informative variables, updates the similarity matrix, and simultaneously achieves interpretable predictions. Theoretical guarantees are provided for S$^2$MAM, including the computing convergence and the statistical generalization bound. Experimental assessments across 4 synthetic and 12 real-world datasets, with varying levels and categories of corruption, validate the robustness and interpretability of the proposed approach.

---

### HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing

Authors: Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Lin Fan, Yilin Zhou, Zikang Wang, Xiaotao Gu, Jie Tang, Hongning Wang, Minlie Huang
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19071v1

Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics. LLM's performance in thousand-words level and open-ended writing is inadequately assessed by traditional reference-based metrics or modern LLM-as-a-judge methods. We propose Tree-of-Writing (ToW), to resolve the implicit inconsistency often found when LLM-as-a-judge aggregates all sub-features in text evaluation. ToW incorporates a tree-structured workflow by explicitly modeling the aggregation weights of sub-features. We also present HowToBench, a large-scale Chinese writing benchmark encompassing 12 genres and 1302 instructions across three task categories: contextual completion, outline-guided writing, and open-ended generation. ToW successfully mitigates the biases, achieving a 0.93 Pearson correlation with human judgments. Furthermore, we detect that both overlap-based text generation metrics and popular LLM-as-a-judge practices are vulnerable to textual disturbances, while ToW is robust to them. We also uncover a negative correlation between input length and content-related scores in the Guide task, showcasing that it cannot be simply improved by input-side information piling.

---

### TRN-R1-Zero: Text-rich Network Reasoning via LLMs with Reinforcement Learning Only

Authors: Yilun Liu, Ruihong Qiu, Zi Huang
Published: 2026-04-21
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.19070v1

Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision. While graph neural networks rely on fixed label spaces and supervised objectives, recent large language model (LLM)-based approaches often overlook graph context or depend on distillation from larger models, limiting generalisation. We propose TRN-R1-Zero, a post-training framework for TRN reasoning trained solely via reinforcement learning. TRN-R1-Zero directly optimises base LLMs using a Neighbour-aware Group Relative Policy Optimisation objective that dynamically adjusts rewards based on a novel margin gain metric for the informativeness of neighbouring signals, effectively guiding the model toward relational reasoning. Unlike prior methods, TRN-R1-Zero requires no supervised fine-tuning or chain-of-thought data generated from large reasoning models. Extensive experiments across citation, hyperlink, social and co-purchase TRN benchmarks demonstrate the superiority and robustness of TRN-R1-Zero. Moreover, relying strictly on node-level training, TRN-R1-Zero achieves zero-shot inference on edge- and graph-level tasks, extending beyond cross-domain transfer. The codebase is publicly available at https://github.com/superallen13/TRN-R1-Zero.

---

### Product-of-Experts Training Reduces Dataset Artifacts in Natural Language Inference

Authors: Aby Mammen Mathew
Published: 2026-04-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.19069v1

Neural NLI models overfit dataset artifacts instead of truly reasoning. A hypothesis-only model gets 57.7% in SNLI, showing strong spurious correlations, and 38.6% of the baseline errors are the result of these artifacts. We propose Product-of-Experts (PoE) training, which downweights examples where biased models are overconfident. PoE nearly preserves accuracy (89.10% vs. 89.30%) while cutting bias reliance by 4.71% (bias agreement 49.85% to 45%). An ablation finds lambda = 1.5 that best balances debiasing and accuracy. Behavioral tests still reveal issues with negation and numerical reasoning.

---

### Age-Dependent Heterogeneity in the Association Between Physical Activity and Mental Distress: A Causal Machine Learning Analysis of 3.2 Million U.S. Adults

Authors: Yuan Shan
Published: 2026-04-21
Categories: cs.LG, stat.AP
arXiv: https://arxiv.org/abs/2604.19066v1

Physical activity (PA) is widely recognized as protective against mental distress, yet whether this benefit varies systematically across population subgroups remains poorly understood. Using pooled data from ten consecutive annual waves of the U.S. Behavioral Risk Factor Surveillance System (2015-2024; n = 3,242,218), we investigate heterogeneity in the association between leisure-time PA and frequent mental distress (FMD, >=14 days/month) across age groups. Survey-weighted logistic regression reveals a striking age gradient: the adjusted odds ratio for PA ranges from 0.89 among young adults (18-24) to 0.50 among adults aged 55-64, with the protective association strengthening monotonically with age. Temporal analysis across all ten years shows that the young-adult PA effect has been eroding over the past decade, with the 18-24 OR reaching 1.01 (null) in both 2018 and 2024 -- paralleling the deepening youth mental health crisis. Causal Forest via Double Machine Learning independently identifies age as the dominant driver of treatment effect heterogeneity (feature importance = 0.39, 2.5x the next predictor). E-value sensitivity analysis, propensity score overlap checks, placebo tests, and imputation comparisons confirm the robustness of the findings. These results suggest that the well-documented exercise--mental health link may not generalize to the youngest adult population, whose distress appears increasingly driven by stressors that PA alone cannot mitigate.

---

### Last-Iterate Guarantees for Learning in Co-coercive Games

Authors: Siddharth Chandak, Ramanan Tamizholi, Nicholas Bambos
Published: 2026-04-21
Categories: cs.GT, eess.SY, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2604.19065v1

We establish finite-time last-iterate guarantees for vanilla stochastic gradient descent in co-coercive games under noisy feedback. This is a broad class of games that is more general than strongly monotone games, allows for multiple Nash equilibria, and includes examples such as quadratic games with negative semidefinite interaction matrices and potential games with smooth concave potentials. Prior work in this setting has relied on relative noise models, where the noise vanishes as iterates approach equilibrium, an assumption that is often unrealistic in practice. We work instead under a substantially more general noise model in which the second moment of the noise is allowed to scale affinely with the squared norm of the iterates, an assumption natural in learning with unbounded action spaces. Under this model, we prove a last-iterate bound of order $O(\log(t)/t^{1/3})$, the first such bound for co-coercive games under non-vanishing noise. We additionally establish almost sure convergence of the iterates to the set of Nash equilibria and derive time-average convergence guarantees.

---

### The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation

Authors: Zhen Liu, Yuhan Liu, Jinjun Wang, Jianyi Liu, Wei Song, Jingwen Fu
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.19064v1

In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends on balancing behavioral diversity and learning stability, which governs whether the agent can extract a reliable learning signal for improvement. Increasing behavioral diversity is necessary to expose alternative action hypotheses but can destabilize policy-induced learning signals, whereas overly conservative stability constraints suppress exploration and induce early commitment, making reliable self-improvement difficult. To address this challenge, we propose Stability-Diversity Balance (SDB), a plug-and-play mechanism for balanced self-improvement in VLN. SDB expands each decision step into multiple latent behavioral hypotheses by applying controlled shifts in the instruction-conditioned hidden states, and then performs reliability-aware soft evaluation and aggregation to retain diverse yet instruction-consistent alternatives during learning. An explicit regularizer further constrains hypothesis interactions, preventing excessive drift or premature collapse of hypothesis diversity and stabilizing self-improvement without discarding training signals. Experiments on R2R, SOON, and REVERIE show consistent improvements; for example, on REVERIE val-unseen, SDB improves SPL from 33.73 to 35.93 and OSR from 51.07 to 54.25.

---

### Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports

Authors: Yishu Wei, Yi Lin, Adam Flanders, George Shih, Yifan Peng
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.19060v1

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease labels followed by Group Relative Policy Optimization (GRPO) to refine predictions by optimizing accuracy and format without reasoning supervision. Across three radiologist-annotated datasets, SFT outperformed baselines and GRPO further improved classification and enhanced reasoning recall and comprehensiveness.

---

### Evaluation of Winning Solutions of 2025 Low Power Computer Vision Challenge

Authors: Zihao Ye, Yung-Hsiang Lu, Xiao Hu, Shuai Zhang, Taotao Jing, Xin Li, Zhen Yao, Bo Lang, Zhihao Zheng, Seungmin Oh, Hankyul Kang, Seunghun Kang et al.
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.19054v3

The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy with constraints such as latency, memory capacity, and energy use. The 2025 challenge featured three tracks: (1) Image classification under various lighting conditions and styles, (2) Open-Vocabulary Segmentation with Text Prompt, and (3) Monocular Depth Estimation. This paper presents the design of LPCVC 2025, including its competition structure and evaluation framework, which integrates the Qualcomm AI Hub for consistent and reproducible benchmarking. The paper also introduces the top-performing solutions from each track and outlines key trends and observations. The paper concludes with suggestions for future computer vision competitions.

---

### Cell-Based Representation of Relational Binding in Language Models

Authors: Qin Dai, Benjamin Heinzerling, Kentaro Inui
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19052v1

Understanding a discourse requires tracking entities and the relations that hold between them. While Large Language Models (LLMs) perform well on relational reasoning, the mechanism by which they bind entities, relations, and attributes remains unclear. We study discourse-level relational binding and show that LLMs encode it via a Cell-based Binding Representation (CBR): a low-dimensional linear subspace in which each ``cell'' corresponds to an entity--relation index pair, and bound attributes are retrieved from the corresponding cell during inference. Using controlled multi-sentence data annotated with entity and relation indices, we identify the CBR subspace by decoding these indices from attribute-token activations with Partial Least Squares regression. Across domains and two model families, the indices are linearly decodable and form a grid-like geometry in the projected space. We further find that context-specific CBR representations are related by translation vectors in activation space, enabling cross-context transfer. Finally, activation patching shows that manipulating this subspace systematically changes relational predictions and that perturbing it disrupts performance, providing causal evidence that LLMs rely on CBR for relational binding.

---

### Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery

Authors: Abhinav Agarwal
Published: 2026-04-21
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2604.19049v1

LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context asymmetry, and a Cross-Model Critic (CMC). Adversarial agents attempt to disprove candidates at each promotion gate; cold-start reviewers are intended to reduce anchoring cascades; cross-family review can catch correlated blind spots that same-family review misses. Over a 31-day campaign across 7 targets (security libraries, the ISO C++ standard, major compilers), the pipeline killed roughly 79% of 171 candidates before advancing to disclosure (retrospective aggregate); on a consolidated-protocol subset (lcms2, wolfSSL; n=30), the prospective kill rate was 83%. Outcomes: 4 CVEs (3 public, 1 embargoed); LWG 4549 accepted to the C++ working paper; 5 merged C++ editorial PRs; 3 compiler conformance bugs; 8 merged security-related fixes without CVE; an RFC 9000 errata filed under committee review; and 1+ FIPS 140-3 normative compliance issues under coordinated disclosure -- all evaluated by external acceptance, not benchmarks. The most instructive failure: ten dedicated reviewers unanimously endorsed a non-existent Bleichenbacher padding oracle in OpenSSL's CMS module; it was killed only by a single empirical test, motivating the mandatory empirical gate. No vulnerability was discovered autonomously; the contribution is external structure that filters LLM agents' persistent false positives. As a preliminary transfer test beyond defect discovery, a simplified cross-family critique variant also solved five previously unsolved SymPy instances on SWE-bench Verified and one SWE-rebench hard task.

---

### SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning

Authors: Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan
Published: 2026-04-21
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2604.19048v1

The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges: (1)Imprecise Routing in the current MoE-LoRA method fails to explicitly match input semantics with expert capabilities, leading to weak expert specialization. (2)Uniform weight fusion strategies struggle to provide adaptive update strengths, overlooking the varying complexity of different tasks. To address these limitations, we propose SAMoRA (Semantic-Aware Mixture of LoRA Experts), a novel parameter-efficient fine-tuning framework tailored for task-adaptive learning. Specifically, A Semantic-Aware Router is proposed to explicitly align textual semantics with the most suitable experts for precise routing. A Task-Adaptive Scaling mechanism is designed to regulate expert contributions based on specific task requirements dynamically. In addition, a novel regularization objective is proposed to jointly promote expert specialization and effective scaling. Extensive experiments on multiple multi-task benchmarks demonstrate that SAMoRA significantly outperforms the state-of-the-art methods and holds excellent task generalization capabilities. Code is available at https://github.com/boyan-code/SAMoRA

---

### RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora

Authors: Hanjun Cho, Jay-Yoon Lee
Published: 2026-04-21
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2604.19047v2

Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity. This mismatch undermines evaluation validity: retrievers can be unfairly undervalued even when they retrieve documents that provide sufficient evidence, because redundancy across documents is not accounted for in evaluation. On the other hand, retrievers that perform well on standard benchmarks often generalize poorly to real-world corpora with highly similar and redundant documents. We present RARE (Redundancy-Aware Retrieval Evaluation), a framework for constructing realistic benchmarks by (i) decomposing documents into atomic facts to enable precise redundancy tracking and (ii) enhancing LLM-based data generation with CRRF. RAG benchmark data usually requires multiple quality criteria, but LLMs often yield trivial outputs. CRRF scores criteria separately and fuses decisions by rank, improving the reliability of generated data. Applying RARE to Finance, Legal, and Patent corpora, we introduce RedQA, where a strong retriever baseline drops from 66.4% PerfRecall@10 on 4-hop General-Wiki to 5.0-27.9% PerfRecall@10 at 4-hop depth, revealing robustness gaps that current benchmarks fail to capture. RARE enables practitioners to build domain-specific RAG evaluations that faithfully reflect real-world deployment conditions.

---

### Learning Lifted Action Models from Unsupervised Visual Traces

Authors: Kai Xi, Stephen Gould, Sylvie Thiébaux
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.19043v2

Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a more challenging setting: learning lifted action models from sequences of state images, without action observation. We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model. We also introduce a mixed-integer linear program (MILP) to prevent prediction collapse and self-reinforcing errors among predictions. The MILP takes the predicted states, actions, and action model over a subset of traces and solves for logically consistent states, actions, and action model that are as close as possible to the original predictions. Pseudo-labels extracted from the MILP solution are then used to guide further training. Experiments across multiple domains show that integrating MILP-based correction helps the model escape local optima and converge toward globally consistent solutions.

---

### Generative Texture Filtering

Authors: Rongjia Zheng, Shangwei Huang, Lei Zhu, Wei-Shi Zheng, Qing Zhang
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.19039v1

We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower texture filtering by taking full advantage of the strong learned image prior of pre-trained generative models. To this end, we propose to fine-tune a pre-trained generative model via a two-stage strategy. Specifically, we first conduct supervised fine-tuning on a very small set of paired images, and then perform reinforcement fine-tuning on a large-scale unlabeled dataset under the guidance of a reward function that quantifies the quality of texture removal and structure preservation. Extensive experiments show that our method clearly outperforms previous methods, and is effective to deal with previously challenging cases. Our code is available at https://github.com/OnlyZZZZ/Generative_Texture_Filtering.

---

### Plausible Reasoning and First-Order Plausible Logic

Authors: David Billington
Published: 2026-04-21
Categories: cs.AI, cs.LO
arXiv: https://arxiv.org/abs/2604.19036v1

Defeasible statements are statements that are likely, or probable, or usually true, but may occasionally be false. Plausible reasoning makes conclusions from statements that are either facts or defeasible statements without using numbers. So there are no probabilities or suchlike involved. Seventeen principles of logics that do plausible reasoning are suggested and several important plausible reasoning examples are considered. There are 14 necessary principles and 3 desirable principles, one of which is not formally stated. A first-order logic, called Plausible Logic (PL), is defined that satisfies all but two of the desirable principles and reasons correctly with all the examples. As far as we are aware, this is the only such logic. PL has 8 reasoning algorithms because, from a given plausible reasoning situation, there are different sensible conclusions. This article is a condensation of my book `Plausible Reasoning and Plausible Logic' (PRPL), which is to be submitted. Each section of this article corresponds to a chapter in PRPL, and vice versa. The proofs of all the results are in PRPL, so they are omitted in this article.

---

### Explore Like Humans: Autonomous Exploration with Online SG-Memo Construction for Embodied Agents

Authors: Xu Chen, Shichao Xie, Zhining Gu, Lu Jia, Minghua Luo, Fei Liu, Zedong Chu, Yanfen Shen, Xiaolong Wu, Mu Xu
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.19034v1

Constructing structured spatial memory is essential for enabling long-horizon reasoning in complex embodied navigation tasks. Current memory construction predominantly relies on a decoupled, two-stage paradigm: agents first aggregate environmental data through exploration, followed by the offline reconstruction of spatial memory. However, this post-hoc and geometry-centric approach precludes agents from leveraging high-level semantic intelligence, often causing them to overlook navigationally critical landmarks (e.g., doorways and staircases) that serve as fundamental semantic anchors in human cognitive maps. To bridge this gap, we propose ABot-Explorer, a novel active exploration framework that unifies memory construction and exploration into an online, RGB-only process. At its core, ABot-Explorer leverages Large Vision-Language Models (VLMs) to distill Semantic Navigational Affordances (SNA), which act as cognitive-aligned anchors to guide the agent's movement. By dynamically integrating these SNAs into a hierarchical SG-Memo, ABot-Explorer mirrors human-like exploratory logic by prioritizing structural transit nodes to facilitate efficient coverage. To support this framework, we contribute a large-scale dataset extending InteriorGS with SNA and SG-Memo annotations. Experimental results demonstrate that ABot-Explorer significantly outperforms current state-of-the-art methods in both exploration efficiency and environment coverage, while the resulting SG-Memo is shown to effectively support diverse downstream tasks.

---

### Intentional Updates for Streaming Reinforcement Learning

Authors: Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis, A. Rupam Mahmood, Richard S. Sutton
Published: 2026-04-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.19033v1

In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in function output. This often leads to instability in the streaming setting (i.e., batch size=1), where stochasticity is not averaged out and update magnitudes can momentarily become arbitrarily big or small. Instead, we propose intentional updates: first specify the intended outcome of an update and then solve for the step size that approximately achieves it. This strategy has precedent in online supervised linear regression via Normalized Least Mean Squares algorithm, which selects a step size to yield a specified change in the function output proportional to the current error. We extend this principle to streaming deep reinforcement learning by defining appropriate intended outcomes: Intentional TD aims for a fixed fractional reduction of the TD error, and Intentional Policy Gradient aims for a bounded per-step change in the policy, limiting local KL divergence. We propose practical algorithms combining eligibility traces and diagonal scaling. Empirically, these methods yield state-of-the-art streaming performance, frequently performing on par with batch and replay-buffer approaches.

---

### Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

Authors: Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park
Published: 2026-04-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.19028v1

One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph datasets. A critical challenge facing GNNs lies in their reliance on labeled training data for each individual graph, a requirement that hinders the capacity for universal node classification due to the heterogeneity inherent in graphs -- differences in homophily levels, community structures, and feature distributions across datasets. Inspired by the success of large language models (LLMs) that achieve in-context learning through massive-scale pre-training on diverse datasets, we introduce NodePFN. This universal node classification method generalizes to arbitrary graphs without graph-specific training. NodePFN learns posterior predictive distributions (PPDs) by training only on thousands of synthetic graphs generated from carefully designed priors. Our synthetic graph generation covers real-world graphs through the use of random networks with controllable homophily levels and structural causal models for complex feature-label relationships. We develop a dual-branch architecture combining context-query attention mechanisms with local message passing to enable graph-aware in-context learning. Extensive evaluation on 23 benchmarks demonstrates that a single pre-trained NodePFN achieves 71.27 average accuracy. These results validate that universal graph learning patterns can be effectively learned from synthetic priors, establishing a new paradigm for generalization in node classification.

---

### Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback

Authors: Qiang Liu, Adrienne Kline, Ermin Wei
Published: 2026-04-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.19024v1

Safe Reinforcement Learning from Human Feedback (Safe RLHF) has recently achieved empirical success in developing helpful and harmless large language models by decoupling human preferences regarding helpfulness and harmlessness. Existing approaches typically rely on fitting fixed horizon reward models from human feedback and have only been validated empirically. In this paper, we formulate safe RLHF as an infinite horizon discounted Con- strained Markov Decision Process (CMDP), since humans may interact with the model over a continuing sequence of interactions rather than within a single finite episode. We propose two Safe RLHF algorithms that do not require reward model fitting and, in contrast to prior work assuming fixed-length trajectories, support flexible trajectory lengths for training. Both algo- rithms are based on the primal-dual method and achieve global convergence guarantees with polynomial rates in terms of policy gradient iterations, trajectory sample lengths, and human preference queries. To the best of our knowledge, this is the first work to study infinite horizon discounted CMDP under human feedback and establish global, non-asymptotic convergence.

---

### On Accelerating Grounded Code Development for Research

Authors: Santosh Ganji
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.19022v1

A major challenge for niche scientific and technical domains in leveraging coding agents is the lack of access to up-to-date, domain- specific knowledge. Foundational models often demonstrate limited reasoning capabilities in specialized fields and cannot inherently incorporate knowledge that evolves through ongoing research and experimentation. Materials scientists exploring novel compounds, communication engineers designing and evaluating new protocols, and bioengineering researchers conducting iterative experiments all face this limitation. These experts typically lack the resources to fine-tune large models or continuously embed new findings, creating a barrier to adopting AI-driven coding agents. To address this, we introduce a framework that gives coding agents instanta- neous access to research repositories and technical documentation, enabling real-time, context-aware operation. Our open-source im- plementation allows users to upload documents via doc-search.dev and includes zed-fork, which enforces domain-specific rules and workflows. Together, these tools accelerate the integration of coding agents into specialized scientific and technical workflows

---

### FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control

Authors: Pingwei Sun, Yuxuan Hu, Jianchao Tan, Xue Wang, Jiaqi Zhang, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai
Published: 2026-04-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.19021v3

Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have demonstrated that the delta rule, an online gradient descent update, enables superior associative recall compared to simple additive updates. While KDA refined the coarse head-wise decay gate into channel-wise decay, the learning rate $β_t$ in the delta update remains a scalar, limiting the model's capacity for dimension-specific adaptation. We introduce FG$^2$-GDN, which replaces the scalar $β_t$ with a channel-wise vector analogous to the transition from SGD to per-coordinate adaptive optimizers such as AdaGrad and Adam. We further propose FG$^2$-GDN+, which decouples the scaling for keys and values, enabling independent control of erasure strength and write strength. Experiments on synthetic and real-world benchmarks show that FG$^2$-GDN and its variant improve associative recall and long-context understanding over GDN and KDA, with comparable computational efficiency.

---

### FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control

Authors: Pingwei Sun, Yuxuan Hu, Jianchao Tan, Xue Wang, Jiaqi Zhang, Yifan Lu, Yerui Sun, Yuchen Xie, Xunliang Cai
Published: 2026-04-21
Categories: cs.LG
arXiv: https://arxiv.org/abs/2604.19021v2

Linear attention mechanisms have emerged as promising alternatives to softmax attention, offering linear-time complexity during inference. Recent advances such as Gated DeltaNet (GDN) and Kimi Delta Attention (KDA) have demonstrated that the delta rule, an online gradient descent update, enables superior associative recall compared to simple additive updates. While KDA refined the coarse head-wise decay gate into channel-wise decay, the learning rate $β_t$ in the delta update remains a scalar, limiting the model's capacity for dimension-specific adaptation. We introduce FG$^2$-GDN, which replaces the scalar $β_t$ with a channel-wise vector analogous to the transition from SGD to per-coordinate adaptive optimizers such as AdaGrad and Adam. We further propose FG$^2$-GDN+, which decouples the scaling for keys and values, enabling independent control of erasure strength and write strength. Experiments on synthetic and real-world benchmarks show that FG$^2$-GDN and its variant improve associative recall and long-context understanding over GDN and KDA, with comparable computational efficiency.

---

### Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control

Authors: Julian Skifstad, Xinyue Annie Yang, Glen Chou
Published: 2026-04-21
Categories: cs.LG, cs.AI, eess.SY, math.OC, stat.ML
arXiv: https://arxiv.org/abs/2604.19018v1

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that ignore how perturbations propagate through transformer layers and lack online error feedback, resulting in suboptimal, open-loop control. To address this, we show empirically that, despite the nonlinear structure of transformer blocks, layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models. Exploiting this property, we model LLM inference as a linear time-varying dynamical system and adapt the classical linear quadratic regulator to compute feedback controllers using layer-wise Jacobians, steering activations toward desired semantic setpoints in closed-loop with minimal computational overhead and no offline training. We also derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance. Using a novel adaptive semantic feature setpoint signal, our method yields robust, fine-grained behavior control across models, scales, and tasks, including state-of-the-art modulation of toxicity, truthfulness, refusal, and arbitrary concepts, surpassing baseline steering methods. Our code is available at: https://github.com/trustworthyrobotics/lqr-activation-steering

---

### AlignCultura: Towards Culturally Aligned Large Language Models?

Authors: Gautam Siddharth Kashyap, Mark Dras, Usman Naseem
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19016v1

Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, models risk generating stereotyped, insensitive, or misleading responses that fail to reflect cultural diversity w.r.t Helpful, Harmless, and Honest (HHH) paradigm. Existing benchmarks represent early steps toward cultural alignment; yet, no benchmarks currently enables systematic evaluation of cultural alignment in line with UNESCO's principles of cultural diversity w.r.t HHH paradigm. Therefore, to address this gap, we built Align-Cultura, two-stage pipeline for cultural alignment. Stage I constructs CULTURAX, the HHH-English dataset grounded in the UNESCO cultural taxonomy, through Query Construction, which reclassifies prompts, expands underrepresented domains (or labels), and prevents data leakage with SimHash. Then, Response Generation pairs prompts with culturally grounded responses via two-stage rejection sampling. The final dataset contains 1,500 samples spanning 30 subdomains of tangible and intangible cultural forms. Stage II benchmarks CULTURAX on general-purpose models, culturally fine-tuned models, and open-weight LLMs (Qwen3-8B and DeepSeek-R1-Distill-Qwen-7B). Empirically, culturally fine-tuned models improve joint HHH by 4%-6%, reduce cultural failures by 18%, achieve 10%-12% efficiency gains, and limit leakage to 0.3%.

---

### FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

Authors: Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang
Published: 2026-04-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.19015v1

Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance bottleneck, leaving a significant gap compared to centralized training. To bridge this gap, we introduce FedProxy, a new federated adaptation framework. FedProxy replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM), compressed from the proprietary LLM, to serve as a high-fidelity surrogate for collaborative fine-tuning. Our framework systematically resolves the trilemma through a three-stage architecture: (i) Efficient Representation via server-guided compression to create a resource-friendly proxy; (ii) Robust Optimization through an interference-mitigating aggregation strategy to handle data heterogeneity; and (iii) Effortless Fusion via a training-free "plug-in" mechanism to integrate learned knowledge back into the LLM. Experiments show FedProxy significantly outperforms OT methods and approaches centralized performance, establishing a new benchmark for secure and high-performance federated LLM adaptation.

---

### Accelerating trajectory optimization with Sobolev-trained diffusion policies

Authors: Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec, Justin Carpentier
Published: 2026-04-21
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2604.19011v2

Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is that each new problem instance is solved independently; therefore, convergence speed and quality of the solution found depend on the initial trajectory proposed. To improve efficiency, a natural approach is to warm-start TO with initial guesses produced by a learned policy trained on trajectories previously generated by the solver. Diffusion-based policies have recently emerged as expressive imitation learning models, making them promising candidates for this role. Yet, a counterintuitive challenge comes from the local optimality of TO demonstrations: when a policy is rolled out, small non-optimal deviations may push it into situations not represented in the training data, triggering compounding errors over long horizons. In this work, we focus on learning-based warm-starting for gradient-based TO solvers that also provide feedback gains. Exploiting this specificity, we derive a first-order loss for Sobolev learning of diffusion-based policies using both trajectories and feedback gains. Through comprehensive experiments, we demonstrate that the resulting policy avoids compounding errors, and so can learn from very few trajectories to provide initial guesses reducing solving time by $2\times$ to $20 \times$. Incorporating first-order information enables predictions with fewer diffusion steps, reducing inference latency.

---

### Guiding Distribution Matching Distillation with Gradient-Based Reinforcement Learning

Authors: Linwei Dong, Ruoyu Guo, Ge Bai, Zehuan Yuan, Yawei Luo, Changqing Zou
Published: 2026-04-21
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2604.19009v1

Diffusion distillation, exemplified by Distribution Matching Distillation (DMD), has shown great promise in few-step generation but often sacrifices quality for sampling speed. While integrating Reinforcement Learning (RL) into distillation offers potential, a naive fusion of these two objectives relies on suboptimal raw sample evaluation. This sample-based scoring creates inherent conflicts with the distillation trajectory and produces unreliable rewards due to the noisy nature of early-stage generation. To overcome these limitations, we propose GDMD, a novel framework that redefines the reward mechanism by prioritizing distillation gradients over raw pixel outputs as the primary signal for optimization. By reinterpreting the DMD gradients as implicit target tensors, our framework enables existing reward models to directly evaluate the quality of distillation updates. This gradient-level guidance functions as an adaptive weighting that synchronizes the RL policy with the distillation objective, effectively neutralizing optimization divergence. Empirical results show that GDMD sets a new SOTA for few-step generation. Specifically, our 4-step models outperform the quality of their multi-step teacher and substantially exceed previous DMDR results in GenEval and human-preference metrics, exhibiting strong scalability potential.

---

### Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

Authors: Yixuan Tang, Yirui Zhang, Hang Feng, Anthony K. H. Tung
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19005v3

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification. The code is available at https://github.com/tangyixuan/RADAR.

---

### Debating the Unspoken: Role-Anchored Multi-Agent Reasoning for Half-Truth Detection

Authors: Yixuan Tang, Yirui Zhang, Hang Feng, Anthony K. H. Tung
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19005v2

Half-truths, claims that are factually correct yet misleading due to omitted context, remain a blind spot for fact verification systems focused on explicit falsehoods. Addressing such omission-based manipulation requires reasoning not only about what is said, but also about what is left unsaid. We propose RADAR, a role-anchored multi-agent debate framework for omission-aware fact verification under realistic, noisy retrieval. RADAR assigns complementary roles to a Politician and a Scientist, who reason adversarially over shared retrieved evidence, moderated by a neutral Judge. A dual-threshold early termination controller adaptively decides when sufficient reasoning has been reached to issue a verdict. Experiments show that RADAR consistently outperforms strong single- and multi-agent baselines across datasets and backbones, improving omission detection accuracy while reducing reasoning cost. These results demonstrate that role-anchored, retrieval-grounded debate with adaptive control is an effective and scalable framework for uncovering missing context in fact verification.

---

### HarmThoughts: A Benchmark for Fine-Grained Harmful Behavior Detection in Reasoning Traces

Authors: Ishita Kakkar, Enze Zhang, Rheeya Uppaal, Junjie Hu
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19001v2

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but unfolds through distinct behavioral steps such as suppressing refusal, rationalizing compliance, decomposing harmful tasks, and concealing risk. However, no existing benchmark captures this process at sentence-level granularity within reasoning traces -- a key step toward reliable safety monitoring, interventions, and systematic failure diagnosis. To address this gap, we introduce HarmThoughts, a benchmark for step-wise safety evaluation of reasoning traces. HarmThoughts is built around our proposed harm taxonomy, comprising 16 functional reasoning behavior categories that capture how reasoning steps contribute to or mitigate harmful outcomes. The dataset consists of 56,931 sentences from 1,018 reasoning traces generated by four model families, each annotated with fine-grained sentence-level behavioral labels. Using HarmThoughts, we analyze harm propagation by composing taxonomy behaviors into safety-failure patterns that characterize how reasoning transitions into harmful execution. We compare white-box and black-box monitors for identifying fine-grained taxonomy behaviors, and further evaluate supervised fine-tuning. While off-the-shelf monitors degrade sharply as behavioral granularity increases, fine-tuning substantially improves performance, highlighting both the difficulty and learnability of fine-grained process-level safety monitoring.

---

### When Safety Fails Before the Answer: Benchmarking Harmful Behavior Detection in Reasoning Chains

Authors: Ishita Kakkar, Enze Zhang, Rheeya Uppaal, Junjie Hu
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.19001v1

Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during reasoning. When jailbroken, harm does not appear instantaneously but unfolds through distinct behavioral steps such as suppressing refusal, rationalizing compliance, decomposing harmful tasks, and concealing risk. However, no existing benchmark captures this process at sentence-level granularity within reasoning traces -- a key step toward reliable safety monitoring, interventions, and systematic failure diagnosis. To address this gap, we introduce HarmThoughts, a benchmark for step-wise safety evaluation of reasoning traces. \ourdataset is built on our proposed harm taxonomy of 16 harmful reasoning behaviors across four functional groups that characterize how harm propagates rather than what harm is produced. The dataset consists of 56,931 sentences from 1,018 reasoning traces generated by four model families, each annotated with fine-grained sentence-level behavioral labels. Using HarmThoughts, we analyze harm propagation patterns across reasoning traces, identifying common behavioral trajectories and drift points where reasoning transitions from safe to unsafe. Finally, we systematically compare white-box and black-box detectors on the task of identifying harmful reasoning behaviours on HarmThoughts. Our results show that existing detectors struggle with fine-grained behavior detection in reasoning traces, particularly for nuanced categories within harm emergence and execution, highlighting a critical gap in process-level safety monitoring. HarmThoughts is available publicly at: https://huggingface.co/datasets/ishitakakkar-10/HarmThoughts

---

### Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees

Authors: Xiaoyang Liu, Zineng Dong, Yifan Bai, Yantao Li, Yuntian Liu, Tao Luo
Published: 2026-04-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.19000v2

Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mathematical statements. In this work, we introduce Decompose, Structure, and Repair (DSR), a neuro-symbolic framework that restructures autoformalization into a modular pipeline. DSR decomposes statements into logical components and maps them to structured operator trees, leveraging this topological blueprint to precisely localize and repair errors via sub-tree refinement. Furthermore, we introduce PRIME, a benchmark of 156 undergraduate and graduate-level theorems selected from canonical textbooks and expertly annotated in Lean 4. Experimental results demonstrate that DSR establishes a new state-of-the-art, consistently outperforming baselines under equivalent computational budgets. The datasets, model, and code are available at https://github.com/XiaoyangLiu-sjtu/DSR.

---

### $R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction

Authors: Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin
Published: 2026-04-21
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2604.18995v2

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redundancy caused by confidence clusters and positional ambiguity, and temporal redundancy caused by repeatedly remasking predictions that have already stabilized. Motivated by these patterns, we propose $R^{2}$-dLLM, a unified framework for reducing decoding redundancy from both inference and training perspectives. At inference time, we introduce training-free decoding rules that aggregate local confidence and token predictions, and finalize temporally stable tokens to avoid redundant decoding steps. We further propose a redundancy-aware supervised fine-tuning pipeline that aligns the model with efficient decoding trajectories and reduces reliance on manually tuned thresholds. Experiments demonstrate that $R^{2}$-dLLM consistently reduces the number of decoding steps by up to 88\% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks. These results validate that decoding redundancy is a central bottleneck in dLLMs, and that explicitly reducing it yields substantial practical efficiency gains. Our code and models are available at https://github.com/GATECH-EIC/R2-dLLM.

---

### AutoAWG: Adverse Weather Generation with Adaptive Multi-Controls for Automotive Videos

Authors: Jiagao Hu, Daiguo Zhou, Danzhen Fu, Fuhao Li, Zepeng Wang, Fei Wang, Wenhua Liao, Jiayi Xie, Haiyang Sun
Published: 2026-04-21
Categories: cs.CV, cs.AI, cs.MM
arXiv: https://arxiv.org/abs/2604.18993v1

Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to balance visual quality and annotation reusability. We present AutoAWG, a controllable Adverse Weather video Generation framework for Autonomous driving. Our method employs a semantics-guided adaptive fusion of multiple controls to balance strong weather stylization with high-fidelity preservation of safety-critical targets; leverages a vanishing point-anchored temporal synthesis strategy to construct training sequences from static images, thereby reducing reliance on synthetic data; and adopts masked training to enhance long-horizon generation stability. On the nuScenes validation set, AutoAWG significantly outperforms prior state-of-the-art methods: without first-frame conditioning, FID and FVD are relatively reduced by 50.0% and 16.1%; with first-frame conditioning, they are further reduced by 8.7% and 7.2%, respectively. Extensive qualitative and quantitative results demonstrate advantages in style fidelity, temporal consistency, and semantic--structural integrity, underscoring the practical value of AutoAWG for improving downstream perception in autonomous driving. Our code is available at: https://github.com/higherhu/AutoAWG

---

### A Multi-Agent Framework with Structured Reasoning and Reflective Refinement for Multimodal Empathetic Response Generation

Authors: Liping Wang, Cheng Ye, Weidong Chen, Peipei Song, Bo Hu, Zhendong Mao
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.18988v1

Multimodal empathetic response generation (MERG) aims to generate emotionally engaging and empathetic responses based on users' multimodal contexts. Existing approaches usually rely on an implicit one-pass generation paradigm from multimodal context to the final response, which overlooks two intrinsic characteristics of MERG: (1) Human perception of emotional cues is inherently structured rather than a direct mapping. The conventional paradigm neglects the hierarchical progression of emotion perception, leading to distorted emotional judgments. (2) Given the inherent complexity and ambiguity of human emotions, the conventional paradigm is prone to significant emotional biases, ultimately resulting in suboptimal empathy. In this paper, we propose a multi-agent framework for MERG, which enhances empathy through structured reasoning and reflective refinement. Specifically, we first introduce a structured empathetic reasoning-to-generation module that explicitly decomposes response generation via multimodal perception, consistency-aware emotion forecasting, pragmatic strategy planning, and strategy-guided response generation, providing a clearer intermediate path from multimodal evidence to response realization. Besides, we develop a global reflection and refinement module, in which a global reflection agent performs step-wise auditing over intermediate states and the generated response, eliminating existing emotional biases and empathy errors, and triggering targeted regeneration. Overall, such a closed-loop framework enables our model to gradually improve the accuracy of emotion perception and eliminate emotion biases during the iteration process. Experiments on several benchmarks, e.g., IEMOCAP and MELD, demonstrate that our model has superior empathic response generation capabilities compared to state-of-the-art methods.

---

### SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

Authors: Xiachong Feng, Yi Jiang, Xiaocheng Feng, Deyi Yin, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Yuxuan Gu, Chonghan Qin, Bing Qin, Lingpeng Kong
Published: 2026-04-21
Categories: cs.AI
arXiv: https://arxiv.org/abs/2604.18982v1

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem: determining how individual utterances contribute to multi-turn dialogue outcomes. Existing approaches directly employ language models to distribute episode-level rewards, yielding attributions that are retrospective and lack theoretical grounding. We propose SAVOIR (ShApley Value fOr SocIal RL), a novel principled framework grounded in cooperative game theory. Our approach combines two complementary principles: expected utility shifts evaluation from retrospective attribution to prospective valuation, capturing an utterance's strategic potential for enabling favorable future trajectories; Shapley values ensure fair credit distribution with axiomatic guarantees of efficiency, symmetry, and marginality. Experiments on the SOTOPIA benchmark demonstrate that SAVOIR achieves new state-of-the-art performance across all evaluation settings, with our 7B model matching or exceeding proprietary models including GPT-4o and Claude-3.5-Sonnet. Notably, even large reasoning models consistently underperform, suggesting social intelligence requires qualitatively different capabilities than analytical reasoning.

---

### AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs

Authors: Joongho Jo, Hyerin Lim, Hanjun Choi, Jongsun Park
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.18980v3

Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. However, the importance difference existing among Gaussian-tile pairs has never been considered in the previous works. In this paper, we propose AdaGScale, a novel viewpoint-adaptive Gaussian scaling technique for reducing the number of Gaussian-tile pairs. AdaGScale is based on the observation that the peripheral tiles located far from Gaussian center contribute negligibly to pixel color accumulation. This suggests an opportunity for reducing the number of Gaussian-tile pairs based on color contribution. AdaGScale efficiently estimates the color contribution in the peripheral region of each Gaussian during a preprocessing stage and adaptively scales its size based on the peripheral score. As a result, Gaussians with lower importance intersect with fewer tiles during the intersection test, which improves rendering speed while maintaining image quality. The adjusted size is used only for tile intersection test, and the original size is retained during color accumulation to preserve visual fidelity. Experimental results show that AdaGScale achieves a geometric mean speedup of 13.8x over original 3D-GS on a GPU, with only about 0.5 dB degradation in PSNR on city-scale scenes.

---

### AdaGScale: Viewpoint-Adaptive Gaussian Scaling in 3D Gaussian Splatting to Reduce Gaussian-Tile Pairs

Authors: Joongho Jo, Hyerin Lim, Hanjun Choi, Jongsun Park
Published: 2026-04-21
Categories: cs.CV
arXiv: https://arxiv.org/abs/2604.18980v1

Reducing the number of Gaussian-tile pairs is one of the most promising approaches to improve 3D Gaussian Splatting (3D-GS) rendering speed on GPUs. However, the importance difference existing among Gaussian-tile pairs has never been considered in the previous works. In this paper, we propose AdaGScale, a novel viewpoint-adaptive Gaussian scaling technique for reducing the number of Gaussian-tile pairs. AdaGScale is based on the observation that the peripheral tiles located far from Gaussian center contribute negligibly to pixel color accumulation. This suggests an opportunity for reducing the number of Gaussian-tile pairs based on color contribution. AdaGScale efficiently estimates the color contribution in the peripheral region of each Gaussian during a preprocessing stage and adaptively scales its size based on the peripheral score. As a result, Gaussians with lower importance intersect with fewer tiles during the intersection test, which improves rendering speed while maintaining image quality. The adjusted size is used only for tile intersection test, and the original size is retained during color accumulation to preserve visual fidelity. Experimental results show that AdaGScale achieves a geometric mean speedup of 13.8x over original 3D-GS on a GPU, with only about 0.5 dB degradation in PSNR on city-scale scenes.

---

### Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

Authors: Yuan Zhuang, Yuexin Bian, Sihong He, Jie Feng, Qing Su, Songyang Han, Jonathan Petit, Shihao Ji, Yuanyuan Shi, Fei Miao
Published: 2026-04-21
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2604.18978v2

Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and instability in replay-based bootstrapped training. In this paper, we propose using Low-Rank Adaptation (LoRA) as a structural regularizer for critic learning. Our approach freezes randomly initialized base matrices and optimizes only the corresponding low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. We evaluate our method across different off-policy RL algorithms, including SAC and FastTD3 based on different network architectures. Empirically, LoRA efficiently reduces critic loss during training and improves overall policy performance, achieving the best or competitive results on most tasks. Extensive experiments demonstrate that our low-rank updates provide a simple and effective form of structural regularization for critic learning in off-policy RL.

---

### STAR-Teaming: A Strategy-Response Multiplex Network Approach to Automated LLM Red Teaming

Authors: MinJae Jung, YongTaek Lim, Chaeyun Kim, Junghwan Kim, Kihyun Kim, Minwoo Kim
Published: 2026-04-21
Categories: cs.CL
arXiv: https://arxiv.org/abs/2604.18976v1

While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses. This paper introduces STAR-Teaming, a novel black-box framework for automated red teaming that effectively generates such prompts. STAR-Teaming integrates a Multi-Agent System (MAS) with a Strategy-Response Multiplex Network and employs network-driven optimization to sample effective attack strategies. This network-based approach recasts the intractable high-dimensional embedding space into a tractable structure, yielding two key advantages: it enhances the interpretability of the LLM's strategic vulnerabilities, and it streamlines the search for effective strategies by organizing the search space into semantic communities, thereby preventing redundant exploration. Empirical results demonstrate that STAR-Teaming significantly surpasses existing methods, achieving a higher attack success rate (ASR) at a lower computational cost. Extensive experiments validate the effectiveness and explainability of the Multiplex Network. The code is available at https://github.com/selectstar-ai/STAR-Teaming-paper.

---

### Ground-Level Near Real-Time Modeling for PM2.5 Pollution Prediction

Authors: Zachary R. Fox, Janet O. Agbaje, Dakotah Maguire, Javier E. Santos, Jeremy Logan, Maggie Davis, Rima Habre, Jim VanDerslice, Heidi A. Hanson
Published: 2026-04-21
Categories: stat.AP, cs.LG
arXiv: https://arxiv.org/abs/2604.18973v1

Air pollution is a worldwide public health threat that can cause or exacerbate many illnesses, including respiratory disease, cardiovascular disease, and some cancers. However, epidemiological studies and public health decision-making are stymied by the inability to assess pollution exposure impacts in near real time. To address this, developing accurate digital twins of environmental pollutants will enable timely data-driven analytics - a crucial step in modernizing health policy and decision-making. Although other models predict and analyze fine particulate matter exposure, they often rely on modeled input data sources and data streams that are not regularly updated. Another challenge stems from current models relying on predefined grids. In contrast, our deep-learning approach interpolates surface level PM2.5 concentrations between sparsely distributed US EPA monitoring stations in a grid-free manner. By incorporating additional, readily available datasets - including topographic, meteorological, and land-use data - we improve its ability to predict pollutant concentrations with high spatial and temporal resolution. This enables model querying at any spatial location for rapid predictions without computing over the entire grid. To ensure robustness, we randomize spatial sampling during training to enable our model to perform well in both dense and sparse monitored regions. This model is well suited for near real-time deployment because its lightweight architecture allows for fast updates in response to streaming data. Moreover, model flexibility and scalability allow it to be adapted to various geographical contexts and scales, making it a practical tool for delivering accurate and timely air quality assessments. Its capacity to rapidly evaluate multiple scenarios can be especially valuable for decision-making during public health crises.

---

### Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation

Authors: Yaowei Zheng, Richong Zhang, Shenxi Wu, Shirui Bian, Haosong Zhang, Li Zeng, Xingjian Ma, Yichi Zhang
Published: 2026-04-21
Categories: stat.ML, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2604.18972v2

We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value surface solves a backward parabolic equation, but the Bellman baseline obtained from one-step recursion is only first-order in the grid width. We estimate the time-dependent generator from multi-step transitions using moment-matching coefficients that cancel lower-order truncation terms, and combine the resulting surrogate with backward regression. The main theory gives an end-to-end decomposition into generator misspecification, projection error, pooling bias, finite-sample error, and start-up error, together with a decision-frequency regime map explaining when higher-order gains should be visible. Across calibration studies, four-scale benchmarks, feature and start-up ablations, and gain-mismatch stress tests, the second-order estimator consistently improves on the Bellman baseline and remains stable in the regime where the theory predicts visible gains. These results position high-order generator regression as an interpretable continuous-time policy-evaluation method with a clear operating region.

---