论文检索

Social Aspects · Accountability, Transparency, and Interpretability

Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low

The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $\Theta(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper asymptotic query complexities for existing unbiased randomized algorithms. Within this framework, we systematically develop a linear-space algorithm that requires $O(\frac{n}{\epsilon^{2}}\log\frac{1}{\delta})$ utility queries to ensure $P(\\|\hat{\boldsymbol\phi}-\boldsymbol\phi\\|\_{2}\geq\epsilon)\leq \delta$ for all commonly used semi-values. In particular, our framework naturally bridges OFA, unbiased kernelSHAP, SHAP-IQ and the regression-adjusted approach, and definitively characterizes when paired sampling is beneficial. Moreover, our algorithm allows explicit minimization of the approximation variance $\mathbb{E}[\\|\hat{\boldsymbol\phi}-\boldsymbol\phi\\|_{2}^{2}]$ for each specific utility function. Accordingly, we introduce the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved approximation variance. All of our theoretical findings are experimentally validated.

Deep Learning · Theory

Shahriar Noroozizadeh, Vaishnavh Nagarajan, Elan Rosenfeld, Sanjiv Kumar

Deep sequence models are said to store atomic facts predominantly in the form of associative memory: a brute-force lookup of co-occurring entities. We identify a dramatically different form of storage of atomic facts that we term as geometric memory. Here, the model has synthesized embeddings encoding novel global relationships between all entities, including ones that do not co-occur in training. Such storage is powerful: for instance, we show how it transforms a hard reasoning task involving an $\ell$-fold composition into an easy-to-learn $1$-step navigation task. From this phenomenon, we extract fundamental aspects of neural embedding geometries that are hard to explain. We argue that the rise of such a geometry, as against a lookup of local associations, cannot be straightforwardly attributed to typical supervisory, architectural, or optimizational pressures. Counterintuitively, a geometry is learned even when it is more complex than the brute-force lookup. Then, by analyzing a connection to Node2Vec, we demonstrate how the geometry stems from a spectral bias that---in contrast to prevailing theories---indeed arises naturally despite the lack of various pressures. This analysis also points out to practitioners a visible headroom to make Transformer memory more strongly geometric. We hope the geometric view of parametric memory encourages revisiting the default intuitions that guide researchers in areas like knowledge acquisition, capacity, discovery, and unlearning.

Theory · Learning Theory

Mehryar Mohri

Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention), complexity classes that often fail to support robust length generalization on sequential problems without intermediate chain-of-thought \citep{hahn2020theoretical, merrill2022saturated}. In this work, we introduce \emph{Rational Transductors}, a dual-stream architecture that augments the Transformer with a matrix-valued recurrence derived from Weighted Finite Automata (WFA). By injecting rational state information into the attention mechanism via a \emph{Deep Rational Injection} scheme, our framework strictly generalizes Transformers to capture all Regular Languages, $\NC^1$-complete problems (such as Boolean Formula Evaluation), and fundamental separations like Parity and Modular Counting, while preserving $O(\log T)$ parallel training efficiency. Theoretical analysis and empirical results demonstrate that Rational Transductors solve the "Regular Gap," enabling robust length generalization on algorithmic tasks where standard Transformers fail, without the sequential computational bottlenecks of traditional RNNs.

Deep Learning · Large Language Models

Sinan Fan, Xiaofeng Sun, Chen Shen, Chenxi Huang, Shaotian Yan, Bing Wang, kaiyuan liu, Xiaosong Yuan, Liang Xie, Wenxiao Wang 等

Large reasoning models (LRMs) achieve remarkable reasoning performance by generating long chains-of-thought (CoT). However, standard supervised fine-tuning (SFT) treats all tokens uniformly, indiscriminately minimizing loss across both essential reasoning steps and those that are noisy, redundant, or instance-specific. This often leads student models to memorize superficial patterns rather than acquire generalizable reasoning capabilities. To better understand this limitation, we introduce \textit{Loss Subspace Attribution}, a gradient decomposition analysis approach that uncovers a striking geometric structure: Gradients corresponding to effective reasoning predominantly lie within a low-rank consensus subspace, while conflicting or unstructured signals dominate the residual subspace. Guided by this insight, we propose \textbf{\textit{Spectral-guided Learning}}, a step-level distillation strategy that uses spectral strength to identify reasoning steps aligned with the consensus subspace and prioritizes their contribution to parameter updates, while suppressing gradients from the residual subspace. Experiments across various LRMs and diverse complex reasoning tasks consistently demonstrate that focusing optimization on the consensus subspace yields more robust and generalizable student models.

Social Aspects · Alignment

Ashton Anderson, Harsh Kumar, Louis Tay, Karina Vold

Contemporary large language models are predominantly trained using reinforcement learning from human feedback (RLHF), optimizing for immediate user approval rather than long-term well-being. This position paper argues that as AI systems increasingly serve socioemotional functions, this optimization strategy poses significant risks. Recent evidence demonstrates that leading models exhibit systematic sycophancy, affirming inappropriate user behaviors and preserving user face at rates far exceeding human baselines, while being approximately 40\% more likely to reinforce incorrect beliefs than their non-RLHF counterparts. We contend that the AI community must fundamentally reconsider training objectives to balance short-term satisfaction with long-term user outcomes. We propose three directions: (1) incorporating longitudinal metrics into training that capture sustained goal attainment and reduced regret rather than momentary preference, (2) enabling explicit user choice among interaction modes (concierge, collaborator, coach) with transparent justification for model pushback, and (3) developing frameworks that provide constructive challenge without paternalism. The recent industry backlashes against both excessive and insufficient model agreeableness underscore the urgency of this shift. We argue that optimizing AI systems for human flourishing, not merely human approval, represents both an ethical imperative and a path to more sustainable, trustworthy AI deployment.

Deep Learning · Large Language Models

Xu Wan, Speed Zhu, Jianwei Cai, Guang Chen, XiMing Huang, Wiggin Zhou, Mingyang Sun

Inference-time scaling has emerged as a critical avenue for enhancing Large Language Model performance, yet real-world deployment is bound by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling reasoning utility as an S-shaped function, we derive a theoretical optimal policy based on a global \textit{shadow price} that dynamically equilibrates resource scarcity. Based on this theory, we propose Difficulty-Aware Budget Allocation (DABA), a market-based mechanism that numerically solves for the exact market-clearing price. Unlike standard methods, DABA implements a Lambert W policy to execute strategic abandonment, sacrificing insolvent tasks to redistribute critical computational resources to solvable complex queries. Extensive experiments on mathematical reasoning benchmarks demonstrate that DABA significantly improves the Pareto frontier of cost versus accuracy. In resource-scarce regimes, DABA achieves up to a 3 times improvement in global accuracy compared to uniform allocation.

General Machine Learning · Evaluation

Maris Basha, Anja T. Zai, Sabine Stoll, Richard Hahnloser

General-purpose audio representations aim to map acoustically variable instances of the same event to nearby points, resolving content identity in a zero-shot setting. Unlike supervised classification benchmarks that measure adaptability via parameter updates, we introduce VocSim, a training-free benchmark probing the intrinsic geometric alignment of frozen embeddings. VocSim aggregates 125k single-source clips from 19 corpora spanning human speech, animal vocalizations, and environmental sounds. By restricting to single-source audio, we isolate content representation from the confound of source separation. We evaluate embeddings using Precision@k for local purity and the Global Separation Rate (GSR) for point-wise class separation. To calibrate GSR, we report lift over an empirical permutation baseline. Across diverse foundation models, a simple pipeline, frozen Whisper encoder features, time–frequency pooling, and label-free PCA, yields strong zero-shot performance. However, VocSim also uncovers a consistent generalization gap. On blind, low-resource speech, local retrieval drops sharply. While performance remains statistically distinguishable from chance, the absolute geometric structure collapses, indicating a failure to generalize to unseen phonotactics. As external validation, our top embeddings predict avian perceptual similarity, improve bioacoustic classification, and achieve state-of-the-art results on the HEAR benchmark. We posit that the intrinsic geometric quality measured here proxies utility in unlisted downstream applications. We release data, code, and a public leaderboard to standardize the evaluation of intrinsic audio geometry.

Applications · Time Series

Han Zhang, Nenggan Zheng

Long-horizon motion prediction under external commands is challenged by latent decision uncertainty, where the internal states governing future behavior are unobservable and evolve stochastically over time. This issue is particularly pronounced in biological agents, whose motion trajectories reflect decision-making processes rooted in underlying cognitive states. To address these challenges, we propose CogSDE, a formulation of the controlled stochastic differential equation (SDE) for modeling instruction-driven latent decision dynamics. The drift term in the SDE incorporates a dual-channel control modulation mechanism, enabling external commands to modulate the latent state evolution. The diffusion term in the SDE adopts a state-dependent operator to model intrinsic uncertainty in latent decision dynamics. Furthermore, we establish a theoretical upper bound on the long-horizon prediction of CogSDE through dissipativity-based analysis. Experiments demonstrate that CogSDE consistently improves predictive accuracy in long-horizon motion generation. Importantly, predicted trajectories remain well aligned with control instructions over extended horizons, a property widely recognized as challenging in long-horizon motion prediction.

Deep Learning · Large Language Models

Zhanming Shen, Jiaqi Hu, Zeyu Qin, Hao Chen, Wentao Ye, Zenan Huang, Yihong Zhuang, Guoshan Lu, Junlin Zhou, Junbo Zhao

Efficient distillation is a key pathway for converting expensive reasoning capability into deployable efficiency, yet in the frontier regime where the student already has strong reasoning ability, naive continual distillation often yields limited gains or even degradation. We observe a characteristic training phenomenon: even as loss decreases monotonically, all performance metrics can drop sharply at almost the same bottle-neck, before gradually recovering. We further uncover a token-level mechanism: confidence bifurcates into steadily increasing Imitation-Anchor Tokens that quickly anchor optimization and other yet-to-learn tokens whose confidence is suppressed until after the bottleneck. And the characteristic that these two types of tokens cannot coexist is the root cause of the failure in continual distillation. To this end, we propose Training-Trajectory-Aware Token Selection (T3S) to reconstruct the training objective at the token level, clearing the optimization path for yet-to-learn tokens. T3 yields consistent gains in both AR and dLLM settings: with only hundreds of examples, Qwen3-8B surpasses DeepSeek-R1 on competitive reasoning benchmarks, Qwen3-32B approaches Qwen3-235B, and T3-trained LLaDA-2.0-Mini exceeds its AR baseline, achieving state-of-the-art performance among all of 16B-scale no-think models.

Social Aspects · Robustness

Kiarash Banihashem, Jeff Michael Giliberti, Prashant Gokhale, Samira Goudarzi, MohammadTaghi Hajiaghayi, Yuhao Liu, Morteza Monemizadeh, Sandeep Silwal

We work in the adaptive query model, where one is given a point set $P \subset \mathbb{R}^d$ and seeks to construct a data structure that can answer correctly and efficiently a sequence of adaptive queries. In this model, an adversary observes the answers returned by the data structure to previous queries $q_1, \ldots, q_{i-1}$ and, based on this information, chooses the next query point $q_i$. This setting captures strong forms of adaptivity that naturally arise in modern machine learning pipelines, and rules out many classical randomized techniques that assume oblivious queries. Our focus is the problem of furthest neighbor search in this adaptive setting, a fundamental problem in several learning tasks, including diversity maximization, outlier and anomaly detection, adversarial example generation, and more. We present the first adversarially robust data structure for $c$-approximate furthest neighbor queries that achieves query time $\tilde{O}(n^{1/c^2} + d)$. This matches the query time of the seminal result by Indyk [SODA'03] for $c$-approximate furthest neighbor in the oblivious setting, and significantly improves upon the $\tilde{O}(n + d)$ query time achieved by using the adaptive distance estimation framework of Cherapanamjeri and Nelson [NeurIPS'20].

Deep Learning · Generative Models and Autoencoders

Nick Dodson, Xinyu Gao, Qingsong Wang, Yusu Wang, Zhengchao Wan

Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research. In particular, it is unclear where along the noise schedule memorization is induced, how data geometry influences it, and how phenomena at different noise scales interact. We introduce a geometric framework that partitions the noise schedule into three regimes based on the coverage properties of training data by Gaussian shells and the concentration behavior of the posterior, which we argue are two fundamental objects governing memorization and generalization in diffusion models. This perspective reveals that memorization risk is highly non-uniform across noise levels. We further identify a danger zone at medium noise levels where memorization is most pronounced. In contrast, both the small and large noise regimes resist memorization, but through fundamentally different mechanisms: small noise avoids memorization due to limited training coverage, while large noise exhibits low posterior concentration and admits a provably near linear Gaussian denoising behavior. For the medium noise regime, we identify geometric conditions through which we propose a geometry-informed targeted intervention that mitigates memorization.

Applications · Computer Vision

Shuaibo Li, Pengfei HAO, Hongtao Wu, Jianfeng Dong, Ping Li, Xiaohong Liu, Lei Zhu

Recent advances in generative video models have blurred the boundary between real and synthetic content, raising urgent concerns about digital authenticity. Multimodal large language models (MLLMs) are appealing for AI-generated video (AIGV) forensics due to their broad perceptual and reasoning capabilities; however, existing MLLM-based detectors still suffer from hallucination and unstable reasoning, yielding high false-alarm rates and generic, non-verifiable explanations. To address these issues, we propose Hermes, an evidence-driven agentic framework for trustworthy and explainable AIGV detection. Hermes is realized by three key capabilities: (1) Adaptive Instance-Conditioned Detection Strategy Planning, (2) Evidence-Centric Reasoning and Verification, and (3) Graph-Grounded Evidence Deliberation. Concretely, Hermes employs an instance-conditioned RAG mechanism to analyze each video and retrieve authenticity-verification knowledge for composing a tailored detection strategy. It then performs evidence-centric reasoning by constructing a verifiable Evidence Reasoning Graph (ERG) that maintains focus on authenticity verification and avoids attention drift or superficial reasoning. Finally, a multi-agent deliberation process audits and refines the ERG to reconcile conflicting evidence and enhance reliability. Supported by these capabilities and a rich library of internal and external forensic tools, Hermes achieves structured, verifiable, and interpretable decision-making. Extensive experiments show that Hermes delivers state-of-the-art performance while producing higher-quality, auditable explanations.

Applications · Computer Vision

Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu, Gim Hee Lee

Surface reconstruction with differentiable rendering has achieved impressive performance in recent years, yet the pervasive photometric ambiguities have strictly bottlenecked existing approaches. This paper presents AmbiSuR, a framework that explores an intrinsic solution upon Gaussian Splatting for the photometric ambiguity-robust surface reconstruction with high performance. Started by revisiting the foundation, our investigation uncovers two built-in primitive-wise ambiguities in representation, while revealing an intrinsic potential for ambiguity self-indication in Gaussian Splatting. Stemming from these, a photometric disambiguation is first introduced, constraining ill-posed geometry solution for definite surface formation. Then, we propose an ambiguity indication module that unleashes the self-indication potential to identify and further guide correcting underconstrained reconstructions. Extensive experiments demonstrate our superior performance in surface reconstruction compared to existing methods across various challenging scenarios, while excelling in broad compatibility. Our code will be made open-source upon acceptance.

Theory · Learning Theory

Arefe Boushehrian, Amir Najafi

Learning distribution families over $\mathbb{R}^d$ is a fundamental problem in unsupervised learning and statistics. A central question in this setting is whether a given family of distributions possesses sufficient structure to be (at least) information-theoretically learnable and, if so, to characterize its sample complexity. In 2018, Ashtiani et al. (2018) reformulated sample compressibility as a structural property of distribution classes, proving that it guarantees PAC-learnability. This discovery subsequently enabled a series of recent advancements in deriving nearly tight sample complexity bounds for various high-dimensional open problems. It has been further conjectured that the converse also holds: every learnable class admits a sample compression scheme, making the two notions to be equivalent. In this work, we establish that sample compressible families remain learnable even from perturbed samples, subject to a set of minimax-necessary and sufficient conditions. In particular, we assume samples are corrupted by an additive independent noise model, and theoretically derive sample complexity bounds for general sample compressible classes in arbitrary dimensions with respect to both $\ell_2$-norm and total variation distance.

Social Aspects · Everything Else

Jessica Dai, Inioluwa Raji, Benjamin Recht, Irene Y. Chen

The need for developing model evaluations beyond static benchmarking, especially in the post-deployment phase, is now well-understood. At the same time, concerns about the concentration of power in deployed AI systems have sparked a keen interest in "democratic" or "public" AI. In this work, we bring these two ideas together by proposing mechanisms for aggregated individual reporting (AIR), a framework for post-deployment evaluation that relies on individual reports from the public. An AIR mechanism allows those who interact with a specific, deployed (AI) system to report when they feel that they may have experienced something problematic; these reports are then aggregated over time, with the goal of evaluating the relevant system in a fine-grained manner. **This position paper argues that individual experiences should be understood as an integral part of post-deployment evaluation, and that the scope of our proposed aggregated individual reporting mechanism is a practical path to that end.** On the one hand, individual reporting can identify substantively novel insights about safety and performance; on the other, aggregation can be uniquely useful for informing action. From a normative perspective, the post-deployment phase completes a missing piece in the conversation about "democratic" AI. As a pathway to implementation, we provide a workflow of concrete design decisions and pointers to areas for future research.

Deep Learning · Other Representation Learning

Hongfei Du, Jiacheng Shi, Sidi Lu, Gang Zhou, Ashley Gao

Integrating large language models (LLMs) into text-to-speech (TTS) systems has improved speech expressiveness, yet controllable emotional expression remains challenging. Existing approaches primarily rely on external conditioning or global activation steering, offering limited insight into how emotional variation is represented internally and restricting fine-grained control. In this work, we analyze emotion-related variation in the speech semantic hidden states of LLM-based TTS models. To this end, we leverage sparse autoencoders (SAEs) to map these representations to sparse latent features and examine their emotion-related activation patterns. Our evaluations indicate that emotional variation is distributed across multiple sparse latent features, revealing a more interpretable internal representation. Building on this observation, we introduce a feature-level intervention framework that enables targeted and bidirectional emotion induction and suppression without modifying backbone parameters. We further show that distinct latent features correlate with specific acoustic attributes (e.g., pitch), suggesting that emotional expression arises from coordinated latent contributions rather than a single global shift.

Applications · Robotics

Hyeonbeom Choi, Daechul Ahn, Youhan Lee, Taewook Kang, Seongwon Cho, Jonghyun Choi

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic control, with test-time scaling (TTS) gaining attention to enhance robustness beyond training. However, existing TTS methods for VLAs require additional training, verifiers, and multiple forward passes, making them impractical for deployment. Moreover, they intervene only at action decoding while keeping visual representations fixed—insufficient under perceptual ambiguity, where reconsidering how to perceive is as important as deciding what to do. To address these limitations, we propose SCALE, a simple inference strategy that jointly modulates visual perception and action based on 'self-uncertainty', inspired by uncertainty-driven exploration in Active Inference theory—requiring no additional training, no verifier, and only a single forward pass. SCALE broadens exploration in both perception and action under high uncertainty, while focusing on exploitation when confident—enabling adaptive execution across varying conditions. Experiments on simulated and real-world benchmarks demonstrate that \method improves state-of-the-art VLAs and outperforms existing TTS methods while maintaining single-pass efficiency.

Social Aspects · Safety

Zhe Liu, Zhe Liu, Wenxin Zhang, Quanchen Zou, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Hao Peng

With the rapid evolution of foundation models, Large Language Model (LLM) agents have demonstrated increasingly powerful tool-use capabilities. However, this proficiency introduces significant security risks, as malicious actors can manipulate agents into executing tools to generate harmful content. While existing defensive mechanisms are effective, they frequently suffer from the over-refusal problem, where increased safety strictness compromises the agent's utility on benign tasks. To mitigate this trade-off, we propose \textsc{SafeHarbor}, a novel framework designed to establish precise decision boundaries for LLM agents. Unlike static guidelines, \textsc{SafeHarbor} extracts context-aware defense rules through enhanced adversarial generation. We design a local hierarchical memory system for dynamic rule injection, offering a training-free, efficient, and plug-and-play solution. Furthermore, we introduce an information entropy-based self-evolution mechanism that continuously optimizes the memory structure through dynamic node splitting and merging. Extensive experiments demonstrate that \textsc{SafeHarbor} achieves state-of-the-art performance on both ambiguous benign tasks and explicit malicious attacks, notably attaining a peak benign utility of 63.6\% on GPT-4o while maintaining a robust refusal rate exceeding 93\% against harmful requests.

Social Aspects · Safety

Zhao Tong, Chunlin Gong, Yiping Zhang, Haichao Shi, Qiang Liu, Xingcheng Xu, Shu Wu, Xiao-Yu Zhang

From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response signifies safe reasoning throughout the entire process. Challenging this assumption, our study reveals that during fake news generation, even when a model rejects a harmful request, its Chain-of-Thought (CoT) reasoning may still internally contain and propagate unsafe narratives. To analyze this phenomenon, we introduce a unified safety-analysis framework that systematically deconstructs CoT generation across model layers and evaluates the role of individual attention heads through Jacobian-based spectral metrics. Within this framework, we introduce three interpretable measures: stability, geometry, and energy to quantify how specific attention heads respond or embed deceptive reasoning patterns. Extensive experiments on multiple reasoning-oriented LLMs show that the generation risk rise significantly when the thinking mode is activated, where the critical routing decisions concentrated in only a few contiguous mid-depth layers. By precisely identifying the attention heads responsible for this divergence, our work challenges the assumption that refusal implies safety and provides a new understanding perspective for mitigating latent reasoning risks.

Social Aspects · Safety

Yixu Wang, Yang Yao, Xin Wang, Yifeng Gao, Yan Teng, Xingjun Ma, Yingchun Wang

Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest that robust safety requires context-invariant alignment, where behavior depends on the underlying intent rather than surface form. Enforcing invariance is difficult in alignment because not all training signals are equally trustworthy; for some prompt variants we can obtain verifiable feedback (e.g., multiple-choice), while for open-ended variants we typically rely on noisy, gameable reward proxies (e.g., learned judges). As a result, standard symmetric invariance regularizers can reduce cross-context discrepancies by lowering performance on reliable variants instead of improving open-ended robustness. To address this, we introduce Anchor Invariance Regularization (AIR), which treats verifiable prompts as anchors and uses a stop-gradient target to regularize only the open-ended variants toward the anchor performance. AIR is implemented as a plug-in auxiliary loss and combined with group-based preference optimization (e.g., GRPO) via heterogeneous prompt grouping. Across Safety, Moral Reasoning, and Math, AIR improves context invariance, boosting in-distribution group accuracy by 12.71% and out-of-distribution consistency by 33.49%, making safety constraints robust to adversarial framings.