论文检索

Deep Learning · Large Language Models

Carla Troper

Recent work uses human cognitive benchmarks to evaluate how LLMs represent concepts, claiming to assess "human-like" understanding. This position paper argues that this approach is misguided: these benchmarks come from narrow, typically Western populations yet are treated as universal standards, despite cross-cultural research showing culture shapes how people think, not just what they think about. LLMs trained on global multilingual data should not be expected to mirror thinking patterns from limited groups. Moreover, LLM outputs can shift with minor changes in prompting, unlike the stable human mental structures these benchmarks were designed to measure. These problems show up as contradictory findings across studies, making benchmark results poor evidence for claims about how LLMs represent concepts. We call for evaluation approaches designed for what LLMs actually are—systems trained on diverse global data—rather than tests measuring how closely they match a single population’s way of thinking.

Optimization · Zero-order and Black-box Optimization

Sichen Wang, Zhipeng Lu

Noisy evolution strategies commonly mitigate ranking uncertainty by improving per-generation fidelity—for example, by allocating budget to resampling candidates or using robust aggregation to stabilize the within-generation ordering. Under strict fixed evaluation budgets, however, any additional intra-generation querying directly reduces the number of generations the algorithm can execute, shortening the optimization trajectory. This dynamic can be characterized as prioritizing fidelity over depth. We propose a paradigm shift in fixed-budget regimes toward depth over fidelity, arguing that the cumulative progress from a long sequence of noise-smoothed updates often outweighs that of a short sequence of rigorously denoised ones. We operationalize this principle via probabilistic elite membership, replacing hard truncation with conditional expected rank weights that integrate over ranking uncertainty. This shifts noise handling from the evaluation stage to the selection stage: rather than repeatedly reevaluating candidates to denoise their objective values, we directly smooth the selection signal driving the update. We instantiate this approach using residual bootstrapping: we perform sparse reevaluations near the selection boundary, store standardized noise residuals in a reusable pool, and generate bootstrap rankings to estimate expected weights. Recognizing that residual pool mismatch constitutes a potential statistical risk, we derive a falsifiable error decomposition and provide runtime diagnostics to ensure estimator validity. To prevent oversmoothing in low-noise regimes, we introduce an adaptive probe-and-switch mechanism that leverages a low-cost rank disagreement metric to dynamically select between standard CMA-ES and our bootstrap-based updates. Extensive evaluations across the COCO bbob-noisy suite and diverse external tasks—including RL policy search and noisy HPO—demonstrate consistent gains. Specifically, in high-misranking regimes constrained by strict budgets, our residual-bootstrap approach achieves substantially steeper progress curves than both uncertainty-handling CMA-ES and fixed-k resampling baselines. These results substantiate a testable thesis: when budgets are limited and ranking uncertainty is high, integrating uncertainty at the selection stage is more sample-efficient than reducing it at the evaluation stage.

Applications · Computer Vision

Yuejiao Su, Xinshen ZHANG, Zhen Ye, Lei Yao, Lap-Pui Chau, Yi Wang

A precise and comprehensive understanding of human-environment interactions in egocentric vision is essential for next-generation intelligent agents, such as assistive robotics. While existing multimodal large language models (MLLMs) support unified reasoning from scene-level analysis to instance-specific grounding, their accuracy and generalization remain limited. To this end, this paper introduces a novel Egocentric Analysis-guided RL-based method (EARL) that employs Group Relative Policy Optimization (GRPO) to enhance the interaction understanding of MLLMs in first-person vision. Specifically, EARL adopts a two-stage parsing framework including coarse-grained interpretation and fine-grained response. The first stage holistically interprets egocentric interactions and generates a structured textual description. The second stage produces the language answer and corresponding pixel-level grounding mask in response to the user query. To bridge the two stages, we extract a global interaction descriptor from the first stage and treat it as a semantic prior, which is then integrated via a novel Analysis-guided Feature Synthesizer (AFS) to support query-oriented reasoning. Furthermore, to effectively guide policy optimization, we design a sophisticated, multi-faceted reward mechanism that incorporates format correctness, answer relevance, and grounding accuracy. Experimental results demonstrate that EARL achieves an impressive 65.48% cIoU on the Ego-IRGBench benchmark for pixel grounding, surpassing previous state-of-the-art RL-based methods by 8.37%. Superior performance in out-of-distribution evaluations further validates EARL's generalization capability.

Probabilistic Methods · Everything Else

Roman Plaud, Alexandre Perez-Lebel, Antoine Saillenfest, Thomas Bonald, Marine Le Morvan, Gael Varoquaux, Matthieu Labeau

Probabilistic models are typically trained using task-agnostic objectives like log-loss, which can lead to significant errors in downstream estimation. This disconnect is especially critical in Inverse Probability Weighting (IPW) for causal inference, where propensity score errors near $0$ and $1$ often lead to high bias and variance. We propose a principled framework for deriving task-specific strictly proper scoring rules by matching the local curvature of the downstream error metric. We apply this to the Average Treatment Effect (ATE) estimation, deriving a closed-form loss and its corresponding canonical probability mapping that can be readily integrated with any model like a neural network or a gradient boosting algorithm. Extensive evaluations on causal inference benchmarks demonstrate that our tailored objective consistently outperforms standard likelihood-based and covariate-balancing approaches.

Marianne Arriola, Volodymyr Kuleshov

Masked discrete diffusion models have improved steadily, but still lag behind autoregressive (AR) models in quality, require fixed-length generation, and cannot exploit key-value (KV) caching. Block Diffusion partially bridges diffusion and AR by unmasking left-to-right token blocks, but sacrifices infilling flexibility and KV caching within blocks. Our key insight is that interpolating generation orderings between autoregression and fully-random decoding, rather than committing to a fixed block length, offers a better interpolation between diffusion and AR. We present a new class of language models, Set Diffusion, comprised of 1) a tighter likelihood bound induced by an order-informed noise process and 2) a causal diffusion architecture that enables KV caching under stochastic token orderings. We bias the noise process toward left-to-right generation, rather than enforcing a strict block factorization, such that tokens can be decoded in sliding-window sets for faster inference and greater flexibility for any-order decoding. Set Diffusion achieves better speed-quality tradeoffs on mathematical reasoning, summarization, and unconditional generation compared to prior diffusion language models while offering stronger infilling performance than Block Diffusion.

Ruiqi Lyu, Alistair Turcan, Bryan Wilder

Concept shift occurs when the distribution of labels conditioned on the features changes between domains, making even a well-tuned ML model to have learned a fundamentally incorrect representation. Identifying these shifted features provides unique insight into how one dataset differs from another, considering the difference may be across a scientifically relevant dimension, such as time, disease status, population, etc. In this paper, we propose SGShift, a model for detecting concept shift in tabular data and attributing reduced model performance to a sparse set of shifted features. We frame concept shift as a feature selection task to learn the features that can explain performance differences between models in the source and target domain. This framework enables SGShift to adapt powerful statistical tools such as generalized additive models, knockoffs, and absorption towards identifying these shifted features. We conduct extensive experiments in synthetic and real data across various ML models and find SGShift can identify shifted features much more accurately than baseline methods, requires few samples in the shifted domain, and is robust to complex cases of concept shift.

Anka Reuel, Avijit Ghosh, Jenny Chim, Andrew Tran, Yanan Long, Jennifer Mickel, Usman Gohar, Srishti Yadav, Pawan Sasanka Ammanamanchi, Mowafak Allaham 等

Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor remain uneven. To characterize this landscape, we conduct the first comprehensive analysis of social impact evaluation reporting, examining 186 first-party release reports and 248 third-party evaluation sources, supplemented by developer interviews. We find a stark division of labor: first-party reporting is sparse, often superficial, and declining in areas like environmental impact and bias, while third-party evaluators provide broader, more rigorous coverage of bias, harmful content, and performance disparities. However, only developers can authoritatively report on data provenance, content moderation labor, costs, and infrastructure, yet interviews reveal these disclosures are deprioritized unless tied to product adoption or compliance. Current practices leave major gaps in assessing societal impacts, underscoring the need for policies that mandate developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure for aggregating third-party evaluations.

Applications · Computer Vision

Shoumeng Qiu, Xinrun Li, Yang Long, Xiangyang Xue, Varun Ojha, Jian Pu

The online construction of vectorized high-definition (HD) maps is a cornerstone of modern autonomous driving systems. State-of-the-art approaches, particularly those based on the DETR framework, formulate this as an instance detection problem. However, their reliance on independent, learnable object queries results in a predominantly local query perspective, neglecting the inherent global representation within HD maps. In this work, we propose \textbf{MapGR} (\textbf{G}lobal \textbf{R}epresentation learning for HD \textbf{Map} construction), an architecture designed to learn and utilize a global representations from queries. Our method introduces two synergistic modules: a Global Representation Learning (GRL) module, which encourages the distribution of all queries to better align with the global map through a carefully designed holistic segmentation task, and a Global Representation Guidance (GRG) module, which endows each individual query with explicit, global-level contextual information to facilitate its optimization. Evaluations on the nuScenes and Argoverse2 datasets validate the efficacy of our approach, demonstrating substantial improvements in mean Average Precision (mAP) compared to leading baselines.

Applications · Computer Vision

Bo Zhao, Yihang Liu, Chenfeng Zhang, Huan Yang, Kun Gai, Wei Ji

Text-guided texture editing aims to modify object appearance while preserving the underlying geometric structure. However, our empirical analysis reveals that even SOTA editing models frequently struggle to maintain structural consistency during texture editing, despite the intended changes being purely appearance-related. Motivated by this observation, we jointly enhance structure preservation from both data and training perspectives, and build TexEditor, a dedicated texture editing model based on Qwen-Image-Edit-2509. Firstly, we construct BlenderTex, a high-quality SFT dataset generated with Blender, which provides strong structural priors for a cold start. Secondly, we introduce StructureNFT, a RL–based approach that integrates structure-preserving losses to transfer the structural priors learned during SFT to real-world scenes. Moreover, due to the limited realism and evaluation coverage of existing benchmarks, we introduce TexBench, a general-purpose real-world benchmark for text-guided texture editing. Extensive experiments on existing Blender-based texture benchmarks and our TexBench show that TexEditor consistently outperforms strong baselines such as Nano Banana Pro. In addition, we assess TexEditor on the general-purpose benchmark ImgEdit to validate its generalization.

Deep Learning · Everything Else

Xinxing Yu, Liying Yang, Hao Mo, Hui Ma, Fang Kai, Ajian Liu, Yanyan Liang

High-curvature regions in 3D point clouds encapsulate critical fine-grained geometric semantics yet exhibit a distinct long-tail sparsity in their spatial distribution. The inherent limitations of polynomial volume growth in Euclidean space frequently render these intricate geometric features challenging to adequately resolve within a uniform-scale feature space. Consequently, these regions are frequently overshadowed by smooth global features dominated by low-curvature regions, thereby limiting the discriminative capacity of the network. To address this issue, we propose PointCHR, a curvature-aware hyperbolic rectification (CHR) for point cloud analysis. Utilising the property of exponential volume expansion in the vicinity of hyperbolic manifolds, CHR presents a learnable curvature-guided radial rectification mechanism. By adaptively projecting high-curvature points towards boundary regions endowed with larger effective embedding capacities, PointCHR effectively mitigates the representation crowding problem inherent in Euclidean settings. Extensive experimentation has demonstrated that PointCHR significantly enhances the ability of backbone to capture fine-grained geometric details, achieving state-of-the-art performance across multiple benchmarks.

Social Aspects · Security

Shayne Longpre, Elaine Zhu, Carson Ezell, Avijit Ghosh, Sean McGregor, Kevin Paeth, Kevin Klyman, Sayash Kapoor, Rishi Bommasani, Ruth Elisabeth Appel 等

Flaw reporting for deployed AI systems is fundamental to identifying system failures and improving AI safety. Yet the AI reporting ecosystem is fragmented: researchers who identify flaws often do not know what or where to report, and groups who receive reports rarely share them with other relevant stakeholders. As a result, good-faith reporters duplicate effort by submitting many different forms, and recipients lack standardized, triage-ready information. We audit 12 reporting systems published by AI developers, cybersecurity groups, and AI flaw aggregators, identifying five recurring design challenges spanning discoverability, scope, information collection, coordination, and guidance for strict-liability cases. Building on this analysis and feedback from 49 experts across 32 organizations representing developers, security researchers, and ecosystem coordinators, we introduce FLARE-AI, an open-source AI flaw reporting system designed for interoperability with existing systems. FLARE-AI streamlines flaw report creation by collecting triage-relevant information through conditional logic and early classification, then enables optional dissemination of standardized, machine-readable reports to multiple developers, coordinators, and incident registries from a single submission. By lowering barriers to reporting AI flaws and improving interoperability across stakeholders, FLARE-AI helps break down silos and accelerate remediation across the AI ecosystem.

Applications · Robotics

Yanbiao Ji, Qiuchang Li, Yuting Hu, Shaokai Wu, Wenyuan XIE, Guodong ZHANG, Qichen He, Deyi Ji, Yue Ding, Hongtao Lu

This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under maximum-entropy optimality, the score function learned via denoising score matching recovers the gradient of the expert's soft Q-function, enabling reward extraction without adversarial training. Formally, we prove that constraining the learned field to be conservative reduces hypothesis complexity and tightens out-of-distribution generalization bounds. We further characterize the identifiability of recovered rewards and bound how score estimation errors propagate to action preferences. Empirically, EnergyFlow achieves state-of-the-art imitation performance on various manipulation tasks while providing an effective reward signal for downstream reinforcement learning that outperforms both adversarial IRL methods and likelihood-based alternatives. These results show that the structural constraints required for valid reward extraction simultaneously serve as beneficial inductive biases for policy generalization. The code is available at https://anonymous.4open.science/r/EnergyFlow-FAE1.

General Machine Learning · Transfer, Multitask and Meta-learning

Yayuan Li, Ze Peng, Jian Zhang, Jintao Guo, Yue Duan, Yinghuan Shi

Model merging combines multiple fine-tuned models into a single model by $\textit{adding}$ their weight updates, providing a lightweight alternative to retraining. Existing methods primarily target resolving conflicts between task updates, leaving the failure mode of over-counting shared knowledge unaddressed. We show that when tasks share aligned spectral directions (\ie, overlapping singular vectors), a simple linear combination repeatedly accumulates these directions, inflating the singular values and biasing the merged model toward shared subspaces. To mitigate this issue, we propose Singular Value Calibration (SVC), a training-free and data-free post-processing method that quantifies subspace overlap and rescales inflated singular values to restore a balanced spectrum. Across vision and language benchmarks, SVC consistently improves strong merging baselines and achieves state-of-the-art performance. Furthermore, by modifying only the singular values, SVC improves the performance of Task Arithmetic by 13.0\%.

Deep Learning · Large Language Models

(Andrew) Zhanke Zhou, Xiangyu Lu, Chentao Cao, Brando Miranda, Tongliang Liu, Bo Han, Sanmi Koyejo

RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often uses uniform sampling and near-uniform weighting, leading to inefficient computation allocation. We study GRPO by tracking token log-probabilities, group-normalized advantages, and induced token-level update weights. This reveals three recurring dynamics: probability inflation, advantage contraction as accuracy rises, and hierarchical convergence, where easy questions quickly saturate while hard questions remain discovery-limited due to rare correct rollouts. These findings imply that the benefit of each update depends strongly on both question difficulty and the model’s current competence. Motivated by this, we propose Confidence and Difficulty-adaptive Policy Optimization (CoDaPO), which assigns each question a bounded value from rollout confidence and empirical difficulty, then uses it to reweight policy updates and resample high-value questions within minibatches to increase discovery under a fixed compute budget. Across seven benchmarks, CoDaPO consistently improves accuracy over other RL methods.

Applications · Computer Vision

Tal Reiss, Daniel Winter, Matan Cohen, Alex Rav-Acha, Yael Pritch, Ariel Shamir, Yedid Hoshen

We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even the shape of an object, while preserving its perceived identity and scene context. Existing approaches either rely on unsupervised priors that often fail to preserve identity or use overly restrictive supervision that prevents meaningful intrinsic variations. Our method relies on: (i) a relaxed training objective that allows the model to change both intrinsic and extrinsic attributes conditioned on an identity reference image, a textual prompt describing the target intrinsic attributes, and a background image and object mask defining the extrinsic context. At inference, we restrict extrinsic changes by reusing the original background and object mask, thereby ensuring that only the desired intrinsic attributes are altered; (ii) Visual Named Entities (VNEs) - fine-grained visual identity categories (e.g., "Porsche 911 Carrera") that group objects sharing identity-defining features while allowing variation in intrinsic attributes. We use a vision-language model to automatically extract VNE labels and intrinsic attribute descriptions from a large public image dataset, enabling scalable, identity-preserving supervision. Alterbute outperforms existing methods on identity-preserving object intrinsic attribute editing.

Social Aspects · Privacy

Yuefeng Peng, Parnian Afshar, Megan Ganji, Thomas Butler, Amir Houmansadr, Mingxian Wang, Dezhi Hong

Large language models can memorize information that must be removed--ranging from copyright-sensitive content (e.g., book chapters) to personally identifiable information (e.g., income)--to ensure responsible and compliant behavior. Unlearning has emerged as an efficient alternative to full retraining, aiming to remove specific knowledge. However, users may still expect model to leverage the removed information when it is re-introduced in the prompt. Existing evaluations of unlearning methods focus on (1) the extent of forgetting of the target knowledge (forget set) and (2) performance preservation on the retain set (i.e., utility), but overlook this critical usability dimension. Through a systematic evaluation of six state-of-the-art unlearning methods, we show that they consistently degrade such \emph{contextual utility}--the model's ability to use forgotten knowledge when it is provided in context. To address this, we augment unlearning objectives with a plug-in term that explicitly preserves contextual utility. Extensive experiments demonstrate that our approach restores contextual utility to near original levels while still maintaining effective forgetting and retain-set utility.

Applications · Computer Vision

Changbin Zhang, Yujie Zhong, Qiang Zhang, Kai Han

While visually grounded Chain-of-Thought (CoT) has emerged as a promising paradigm to enhance fine-grained perception in multimodal large language models (MLLMs), its efficacy during the inference phase remains under-scrutinized. In this work, we empirically find that mandating the explicit object boxes in visually grounded CoT during inference often degrades performance compared to standard textual CoT---which reasons without explicit visual grounding. We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding imposes unnecessary task interference, which detracts from the model's primary focus on answer prediction. To address this problem, we propose Internalizing Visually Grounded Reasoning (**iVGR**), a novel reinforcement learning framework that transfers localization capabilities into the textual reasoning process. We employ a dual-stream training strategy, where a textual stream is aligned with a high-quality (visually) grounded stream via a proposed consistency reward, enabling the model to localize accurately without explicit grounding during inference. Extensive experiments on Qwen2.5-VL and Qwen3-VL demonstrate that our method significantly outperforms existing baselines on fine-grained benchmarks, while maintaining the flexibility to support tool-assisted inference workflows.

Applications · Everything Else

Pawan Sasanka Ammanamanchi, Siddharth Bhat, Stella Biderman

Benchmarks for LLM-assisted theorem proving in Lean are often treated as intrinsically reliable because every solved instance comes with a machine-checked proof. However, the kernel only checks that a proof establishes a \emph{formal} statement; it does not verify that the statement faithfully encodes the intended informal problem, nor that evaluation harnesses are robust to trivial or adversarial solutions. We audit widely used Lean theorem-proving benchmarks and find recurring defects in every dataset we examined, including missing hypotheses, problem simplification, incomplete or incorrect translations, and Lean-specific specification hazards. Beyond dataset construction, we survey and identify evaluation-time failure modes that can inflate reported success without demonstrating meaningful proof capability. We propose a fault taxonomy, a suite of automated checkers and prompts, and release standards to guide the creation of formal math datasets and make evaluation more reproducible and trustworthy.

Social Aspects · Security

Changyue Jiang, Wenqi Zhang, Xudong Pan, Geng Hong, Min Yang

LLM-based agents solve complex tasks through iterative reasoning, tool use, and environment interaction, where each intermediate thought directly shapes subsequent actions. Small deviations in these thoughts can therefore propagate into unsafe behaviors, yet existing guardrails typically operate only on final outputs or require intrusive model modifications. We introduce Thought-Aligner, a lightweight plug-in safety model that performs causal correction on unsafe thoughts before action execution, without altering the underlying agent. The corrected thoughts are fed back into the agent, steering its decision process and tool use toward safer trajectories. Because it operates solely at the thought level, Thought-Aligner is model-agnostic and can be integrated into diverse agent frameworks. We train Thought-Aligner via two-stage contrastive learning on paired safe and unsafe thoughts generated across ten risk scenarios. Experiments on two agent-safety benchmarks with six LLMs show that Thought-Aligner increases behavioral safety from about 50% without protection to around 90% on average, exceeding state-of-the-art guardrails by roughly 23%, while also improving helpfulness by about 5%. The method incurs low per-step latency and minimal overhead, enabling scalable and practical deployment.

Reinforcement Learning · Deep RL

Po-Nien Kung, Zhen Yang, Jeffrey Luo, Cheng-Fu Yang, Haikang Deng, Zi-Yi Dou, Yinfei Yang, Nanyun Peng, Zhe Gan, Kai-Wei Chang

Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., “wait,” indicating verification). However, complex reasoning trajectories remain sparse in unconstrained sampling, and standard RL often fails to guarantee the acquisition of diverse reasoning behaviors. We propose a systematic discovery and reinforcement of diverse reasoning patterns through structured reasoning, a paradigm that requires targeted exploration of specific reasoning patterns during the RL process. To this end, we propose Ctrl-R, a framework for learning structured reasoning via tractable trajectory control that actively guides the rollout process, incentivizing the exploration of diverse reasoning patterns that are critical for complex problem-solving. The resulting behavior policy enables accurate importance-sampling estimation, supporting unbiased on-policy optimization. We further introduce a power-scaling factor on the importance-sampling weights, allowing the policy to selectively learn from exploratory, out-of-distribution trajectories while maintaining stable optimization. Experiments demonstrate that Ctrl-R enables effective exploration and internalization of previously unattainable reasoning patterns, yielding consistent improvements across language and vision–language models on mathematical reasoning tasks.