NeurIPS 2026 论文列表

A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: \emph{measure mismatch}, where the benchmark difficulty distribution differs from the intended difficulty distribution, and \emph{coverage gaps}, where uncovered regions along the difficulty axis prevent benchmarks from detecting meaningful localized training progress. We propose two diagnostic metrics that capture these two failure modes and provide rigorous theoretical guarantees. Empirically, we analyze \textbf{25} popular benchmarks spanning \textbf{7} domains using carefully estimated item difficulties. Our results show that many benchmarks implicitly overweight certain difficulty regions, so their leaderboard conclusions should be interpreted with caution; others leave substantial portions of the difficulty axis uncovered, limiting their ability to monitor model improvement process. Finally, we turn diagnosis into action by introducing \textsc{BenchFill}, a simple difficulty-targeted item rewriting algorithm that effectively reduces local coverage gaps.

Microsoft Word is a central environment for office automation, yet evaluating whether an agent has correctly edited a Word document remains difficult. Unlike plain text generation, Word editing changes a structured document object, where formatting, lists, fields, layout, and object properties may all be part of the requested effect. Existing evaluation protocols based on whole-document text similarity, rendered visual similarity, or LLM-as-a-judge scores cannot reliably determine whether the requested Word-native effect is realized as editable document state or whether relevant surrounding state is preserved. We introduce WordEval, a benchmark for evaluating Word-native document editing from natural-language instructions. Each case consists of an input .docx file and an editing instruction; the evaluator compares the agent’s output with a reference document using deterministic checks over Word-readable object properties. WordEval is constructed by design from planned editing units, rather than sampled from arbitrary documents: each unit specifies an input precondition, target object, operation, parameters, reference-generation procedure, and oracle specification. The current release contains 642 cases, including 546 atomic cases over 231 Word commands and 96 compositional cases instantiated from 27 composition templates. Its analysis layer covers 140 unique object-property pairs across 65 Word COM objects and 15 document subsystems. The compositional cases are linked to corresponding atomic cases for their component operations, allowing analyses of whether failures arise from individual operations or from combining multiple operations in one document. By combining controlled document construction, reference-based evaluation, and command-grounded deterministic oracles, WordEval provides a fine-grained testbed for measuring Word-native document automation.

As AI development increasingly involves models adapted to downstream settings, a new algorithmic challenge for developers has surfaced: deciding when to adopt model updates. Currently, the only reliable approach is to retrain on new upstream models and then evaluate extensively, which can be prohibitively expensive. We introduce a framework for assessing when to propagate newly released model versions to downstream applications that does not require access to upstream data or retraining a priori. Our framework incorporates geometric similarity and information-theoretic sufficiency to determine when an upstream update substantially shifts the representational basis recruited for a downstream task. This enables targeted update adoption, and supports emerging norms for coordinating AI supply chain infrastructure.

Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, *e.g.*, excessive reasoning on simple questions or insufficient reasoning on complex ones, leading to suboptimal reasoning capabilities. This paper presents the Laws of Reasoning (LoRe), a unified framework that formalizes intrinsic reasoning patterns in ideal LRMs. We first propose *compute law* with the hypothesis that the reasoning compute should scale linearly with question complexity. Beyond compute, we extend LoRe with a supplementary *accuracy law*, positing exponential decay of accuracy with increasing complexity. Since the complexity is difficult to quantify in practice, we approximate these hypotheses via two tractable properties, *monotonicity* and *compositionality*. We therefore introduce LoRe-Bench, a benchmark that systematically measures these properties for large reasoning models. Evaluation shows that most reasoning models exhibit reasonable monotonicity but lack compositionality. In response, we develop an effective finetuning approach that enforces compute-law compositionality. Extensive empirical studies demonstrate that better compliance with compute laws yields consistently improved reasoning performance on multiple benchmarks, and uncovers synergistic gains across properties and laws.

Clustering is a central tool for discovering latent structure in unlabeled data, yet modern clustering pipelines often end with a hard assignment of each observation to a cluster without rigorous measures of assignment uncertainty. We propose a novel weighted conformal approach for constructing confidence sets for cluster labels. The key difficulty is that the labels available for calibration are not observed ground-truth labels, but synthetic labels produced by a data-dependent clustering algorithm. Our method develops a conformal inference algorithm that corrects the resulting mismatch with the latent target labels through weights by formulating conformal clustering as a conditional label-distribution shift problem. We first derive an oracle procedure that attains finite-sample marginal coverage and then develop a computationally tractable and implementable version using estimated conditional label probabilities and augmented calibration. We show that the coverage of the estimated-weight procedure depends on the estimator, giving an explicit bound on the loss relative to the nominal level. Empirical studies beyond the mixture-model settings, explored by the recently developed stochastic split conformal clustering procedure, demonstrate that the proposed weighted approach offers improvements in non-linear and high-dimensional clustering applications in terms of set size.

The advancement of speech technology has predominantly favored high-resource languages, creating a significant digital divide for speakers of most Sub-Saharan African languages. To address this gap, we introduce WAXAL, a large-scale, openly accessible speech dataset for 24 languages (spanning 19 for ASR and 13 for TTS, with overlaps) representing over 100 million speakers. The collection consists of an Automatic Speech Recognition (ASR) dataset containing approximately 2,340 hours of transcribed, image-prompted natural speech (over 14,100 hours of total collected audio) from a diverse range of speakers, and a Text-to-Speech (TTS) dataset with over 235 hours of high-quality, single-speaker studio recordings of phonetically balanced scripts. Crucially, this effort was executed in partnership with four African academic and community organizations, with the explicit goal of building the local ecosystem for speech technology and seeding data collection capabilities within these institutions. To demonstrate the dataset's utility, we benchmark three architecturally distinct ASR models---Gemma 3n-2B, Whisper-Large-v3, and MMS-1b-all---across the 19 ASR languages. Fine-tuning on WAXAL yields substantial improvements, reducing the macro-average Word Error Rate (WER) by up to 61\% (e.g., from 1.23 to 0.48 for Whisper). Models fine-tuned solely on WAXAL also generalize to the independently collected FLEURS benchmark, confirming the dataset's value for domain-transferable ASR adaptation. Furthermore, we employ an LLM-as-judge framework to evaluate semantic meaning preservation, demonstrating that fine-tuned predictions successfully capture core intents of native speakers. The WAXAL datasets are released at https://huggingface.co/datasets/google/WaxalNLP under the CC-BY-4.0 license to catalyze research and the development of inclusive speech technologies for speakers of African languages.

Artificially generated speech is increasingly embedded in everyday life. Voice cloning in particular enables applications where identity preservation is important, such as completing a recording, dubbing in a new language, or preserving the voices of individuals with speech loss. However, in our work, we find that despite the term, voice cloning does not faithfully "clone" an individual's voice. Instead, we find that widely-used voice cloning models systematically apply style transfer to source voices. As rated by human annotators, cloned voices are perceived as more authoritative, warm, customer-service-like, and human-like compared to their sources. Human annotators also report greater trust in cloned voices than source voices, and a greater willingness to disclose sensitive personal information to them. Our work furthermore shows that voice cloning leads to homogenization of speaker characteristics, as measured by reduced variance in accent, speaking rate, and the audio embedding space. Together, our results highlight a new set of limitations and risks of voice cloning technology and their potential impact on human behavior.

Recent audio-language models are increasingly evaluated on recognizing, describing, and reasoning about audio, but expert-facing applications require a different capability: producing feedback that identifies problems and suggests corrective actions grounded in the input. We introduce VocalCoachBench, a benchmark for evaluating audio-language models on expert vocal coaching feedback for singing. VocalCoachBench contains 515 recordings annotated by 18 professional vocal trainers, yielding 1,056 expert submissions and 12,051 atomic coaching claims. It comprises a same-song subset for controlled comparison and a diverse-song subset for segment-grounded feedback across varied songs and recording conditions. To accommodate the open-ended nature of expert feedback, VocalCoachBench separates deterministic structured targets from claim-based assessment of free-form diagnosis and corrective guidance. Human annotation analysis shows that expert agreement varies strongly with label granularity, motivating hierarchical structured metrics and claim-based evaluation of open-ended feedback. Experiments with 12 recent audio-language models reveal a consistent gap: while models can compare performances and identify broad issue domains in free-form feedback, Top-3 fine-grained issue-label identification remains below label-prior baselines and strict diagnosis alignment stays below 7%. To our knowledge, VocalCoachBench provides the first public testbed for evaluating audio-grounded expert feedback for singing, moving audio-language evaluation beyond description toward analytic feedback.

Real-world visualization requests are routinely ambiguous, incomplete, or factually incorrect, yet existing Text-to-Visualization (Text-to-Vis) systems assume well-specified inputs and produce charts in a single pass. When queries are imperfect, a system must interact with the user to recover the true intent, but no benchmark or method supports this dynamic process. We introduce VisInteract, a new paradigm that reframes Text-to-Vis as interaction-driven intent recovery, and VisInteract-Bench, to our knowledge, that is the first benchmark for dynamic interactive Text-to-Vis, featuring controlled imperfection injection, a leakage-controlled User Agent for realistic multi-turn feedback, and dual-perspective (code and chart) automated evaluation. On the algorithmic side, we propose Vis-MCTS, a Monte Carlo Tree Search (MCTS) enhanced method, introducing improvements over classical MCTS, that Progressive Widening to tame the unbounded tool-argument space in tree search, cross-rollout information sharing so clarifications and critiques benefit the entire search tree, and Dimension-Aware Reward Decomposition that routes scalar user feedback along data-fidelity, visual-design, and intent-alignment dimensions to resolve credit assignment across heterogeneous actions. Extensive Experiments across two LLM backbones show that Vis-MCTS consistently outperforms all Text-to-Vis baselines, improving end-to-end task success by 13.40\%--16.27\% over the strongest interactive baseline and by more than 5\times over non-interactive ones.

Neural network-based virtual microphone estimation (neural-VME) synthesizes microphone signals at unobserved spatial locations from a limited set of real microphone (RM) physical recordings. This enables high-resolution arrays that improve spatial processing for downstream tasks such as speech enhancement. However, existing methods rely on supervised training with ground-truth signals captured at virtual locations, requiring datasets that scale with the number of virtual microphones (VM) and leaving open the question of how to design optimal large-array configurations. We propose \textit{Virtual-Flow}, a flow-matching framework that implicitly generates VM signals conditioned on real recordings, without requiring ground-truth targets. We introduce an unsupervised training strategy based on pseudo-VM targets constructed from time-delayed superpositions of real recordings, and show that it improves magnitude estimation in high-frequency bands, yielding richer spatial cues for beamforming. Experiments demonstrate that the proposed Virtual-Flow, combined with reflow distillation, outperforms existing state-of-the-art neural-VME models on downstream neural beamforming and speech enhancement tasks while requiring lower computational load.

We introduce VSRo-200, the first large-scale dataset for visual speech recognition (lip reading) in Romanian, comprising 200 hours of real-world podcast videos. All samples are annotated with pseudo-labels generated by a fine-tuned Romanian ASR model, while a subset of 100 hours is additionally transcribed by humans, enabling controlled analysis of supervision quality under a unified framework. Building on this dataset, we establish a benchmark for visual speech recognition in low-resource settings. We systematically study the impact of supervision quality, showing that while human annotations provide better performance at fixed data scales, pseudo-labels enable continued improvements through scalability. We further evaluate robustness under domain shift using curated out-of-distribution (OOD) test sets, and analyze audio-visual speech recognition (AVSR) under noisy conditions, where multimodal fusion significantly improves robustness compared to audio-only models. Finally, we demonstrate that representations learned on VSRo-200 transfer effectively to the LRRo benchmark for isolated word recognition, substantially outperforming previously reported results. Overall, VSRo-200 provides a new testbed for studying supervision, domain generalization, and multimodal fusion in low-resource visual speech recognition.

Byte-level byte-pair encoding (BBPE) tokenizers are attractive for large language models (LLMs) in multilingual settings because they cover all Unicode text. Under UTF-8, however, many scripts start from a higher byte-level fallback cost than English: when no learned merge covers a character $c$, the tokenizer must emit multiple byte-derived symbols. We call this worst-case pre-merge cost the encoding floor: $$ f(c) = |\\mathrm{utf8}(c)| \\in \\{1,2,3,4\\}. $$ A higher floor inflates token budgets, shrinks usable context, and increases per-request cost. Changing the underlying text encoding can reduce this gap, but a single global encoding can also make already-efficient English spans more expensive in mixed-script text. We propose Universal Byte-Level Encoding (UBE), a dual-alphabet tokenizer with deterministic per-character routing: $$ r(c) = \\begin{cases} \\mathrm{UTF\\text{-}8}, & |\\mathrm{utf8}(c)| \\leq 2,\\\\ \\mathrm{UTF\\text{-}16}, & |\\mathrm{utf8}(c)| > 2. \\end{cases} $$ Characters satisfying $|\\mathrm{utf8}(c)| \\leq 2$ stay on the UTF-8 path, while characters satisfying $|\\mathrm{utf8}(c)| > 2$ are routed through UTF-16. This reduces token costs for Basic Multilingual Plane (BMP) scripts whose characters typically satisfy $|\\mathrm{utf8}(c)| = 3$ and have the highest token premiums, without raising costs for already-efficient spans. UBE changes only the byte representation presented to byte-pair encoding (BPE): the BPE merge rule remains standard, and exact decoding $\\mathrm{decode}(\\mathrm{encode}(s)) = s$ is preserved. Across intrinsic tokenization evaluations, UBE reduces cross-lingual dispersion in English-normalized token-count ratios $\\pi(\\ell) = m(\\ell)/m(\\mathrm{en})$, lowering cross-script token-budget disparity. In multilingual language model experiments, UBE preserves LM quality within seed variability. In the main multilingual settings, UBE reduces token counts most for high-premium scripts and also slightly lowers English token counts; these reductions translate into more usable context under fixed token budgets and faster content-matched prompt processing.

As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context processing, several novel low-complexity hybrid architectures have recently been proposed, effectively alleviating the computational burden of long-context inference. However, existing research on long-context prefill acceleration remains predominantly focused on sparse attention mechanisms, which achieve their maximum speedup only on full-attention models. When transferred to emerging architectures — such as linear/full attention hybrids or sliding window/full attention hybrids — these prefill acceleration approaches suffer significant performance degradation. Furthermore, such methods are generally incompatible with continuous batching, making them difficult to integrate into modern inference engines such as vLLM. To this end, we propose UniPrefill, a prefill acceleration framework applicable to virtually any model architecture, which directly accelerates the model's computation at the token level. We further implement UniPrefill as a continuous batching operator and extend vLLM's scheduling strategy to natively support prefill-decode co-processing for UniPrefill, enabling its seamless integration into vLLM. UniPrefill achieves up to 2.1x speedup in Time-To-First-Token (TTFT), with the acceleration becoming increasingly pronounced as the number of concurrent requests grows.

The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniClawBench, the first capability-driven benchmark designed to evaluate proactive agents in dynamic, real-world settings. UniClawBench is built around five foundational model capabilities: Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, and Cross-Platform Coordination. Based on these capabilities, we design 400 bilingual real-world tasks. Unlike previous benchmarks that rely on static, pre-recorded answers, our benchmark evaluates agents in live Docker containers using fine-grained, step-by-step completion checkpoints. Furthermore, we design a closed-loop evaluation strategy comprising an executor agent, a hidden supervisor agent, and a user agent to simulate realistic multi-turn human feedback without leaking grading criteria. To disentangle base model capabilities from framework-level design choices, we evaluate state-of-the-art models under multiple agent frameworks. Through comprehensive comparisons across both models and frameworks, we show how base model capabilities and agent framework designs jointly shape performance in real-world environments.

Equilibrium Propagation (EP) is a training framework for energy-based models (EBMs) that has attracted interest in the context of neuromorphic computing platforms such as continuous Hopfield networks, nonlinear resistive networks and coupled phase oscillators. However, EP's practical applications have so far remained limited to relatively small-scale problems. Predictive coding networks (PCNs), another class of EBMs rooted in computational neuroscience, are typically trained with a specialized algorithm and have likewise not yet been demonstrated at large scale. In this work, we develop a more effective training method for PCNs which combines the centered variant of EP with a novel equilibration scheme for PCNs. Using this approach, we train a 10-layer convolutional PCN (VGG10) on full-size ImageNet, achieving 13.23% test error rate on the top-5 classification task, close to the 12.2% backpropagation baseline. To our knowledge, this is the first demonstration of both PCNs and EP-based training at ImageNet scale. These results significantly extend the scalability of both approaches and suggest that the primary challenges in scaling EP in other EBMs may not be attributed to inherent limitations of the EP framework.

Training quality is the primary determinant of reasoning efficiency in large language models, yielding greater returns than proportional increases in inference computation. Evaluating 44 language models (0.5B--685B parameters) across six reasoning benchmarks totalling over 67000 assessments, this study establishes when additional inference tokens are beneficial, redundant or actively harmful. Standard models exhibit near-universal accuracy convergence at approximately 1000 tokens regardless of architecture or parameter count. Causal intervention experiments demonstrate that constraining generation length improves reasoning accuracy by 15.4 percentage points, identifying over-generation rather than capacity exhaustion as the primary efficiency bottleneck. Among 13 reasoning-specialised models, training methodology yields 18.8-fold efficiency improvement at matched parameter scales, exceeding gains from ten-fold parameter increases. Graduate-level evaluation reveals that arithmetic benchmark performance does not predict reasoning capability on complex tasks ($r = -0.03$, $P = 0.91$), exposing fundamental limitations invisible to standard evaluation practice. Mechanistic profiling reveals two orthogonal dimensions of training quality---quality control and decomposition efficiency---that independently predict efficiency profiles, providing a measurable framework linking training decisions to inference-time behaviour.

We present the Multi-Block DC (BDC) class, a rich class of structured nonconvex functions that admit a DC (``difference-of-convex'') decomposition across parameter blocks. This multi-block class not only subsumes the usual DC programming, but also turns out to be provably more powerful. Specifically, we demonstrate how standard models (e.g., polynomials and tensor factorization) must have DC decompositions of exponential size, while their BDC formulation is polynomial. This separation in complexity also underscores another key aspect: unlike DC formulations, obtaining BDC formulations for problems is vastly easier and constructive. We illustrate this aspect by presenting explicit BDC formulations for modern tasks such as deep ReLU networks, a result with no known equivalent in the DC class. Moreover, we complement the theory by developing algorithms with non-asymptotic convergence theory, including both batch and stochastic settings, and demonstrate the broad applicability of our method through several applications.

Tool-using language model agents are usually evaluated by whether they finish the user's task. That metric misses a common failure: an agent can complete the requested work while also taking an unauthorized side-effecting action, such as writing to the wrong object, expanding the scope of the request, or contacting an unintended recipient. We call this failure mode collateral damage (CD). We introduce SABench (Side-effect-Aware Benchmark), a benchmark of 201 email, calendar, and ticket tasks. Each task crosses one of four state structures (independent, dependent, externally reachable, cross-tool) with one of four trap families (ambiguity, mis-targeting, cascade harm, overreach), and each task has a deterministic trace-based oracle for both goal satisfaction and authorization compliance. Across 2,211 model-task pairs from 11 frontier LLMs spanning major commercial and open model families, 15.2% of all runs incur CD, with risk concentrated in ambiguity tasks (38.8% violation rate) while non-ambiguous traps average 8.4% CD. Among goal-satisfied runs, 12.8% still produce unauthorized writes. Cross-tool and dependent states have about twice the CD rate of independent states. CD rates vary by 4.7x across models at comparable goal rates, which suggests that task success alone is a poor proxy for safe tool use. The SABench task corpus is released at https://huggingface.co/datasets/anon-sabench-2026/sabench; the traces, oracle, code, and analysis pipeline are released at https://anonymous.4open.science/r/sabench-artifact.

While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal methods are inherently designed for offline settings, limiting their applicability in streaming scenarios due to two fundamental flaws. First, they lack robust mechanisms to manage continuously growing audio-visual context over long horizons and cannot autonomously initiate responses at opportune moments. Second, existing benchmarks are predominantly confined to offline, single-turn question answering, failing to capture continuous, multi-turn streaming interactions. To bridge these gaps, we propose StreamOV, a novel Streaming Omni-Video understanding framework for efficient online audio-visual reasoning with bounded memory and proactive response triggering. Specifically, StreamOV introduces a multimodal evidence-guided long-short term memory that condenses historical audio-visual context into compact informative evidence under a fixed budget. It further employs a hidden-state-driven trigger to decide when to respond, avoiding explicit silence-token generation and external routers. We also curate SOVBench, the first comprehensive benchmark for online, multi-turn omni-modal evaluation. Extensive experiments show that StreamOV achieves state-of-the-art performance across diverse streaming and omni-video benchmarks, demonstrating its effectiveness for both online and offline video understanding.