NeurIPS 2026 论文列表

This paper studies the $\varepsilon$-best arm identification problem ($\varepsilon$-BAI) for $K$-armed bandits under the fixed-confidence setting. Departing from the usual objective of identifying the best arm with minimal sample complexity, we focus on minimizing the cumulative regret of identifying an $\varepsilon$-best arm. We consider the usual asymptotic regime in which the error probability $\delta$ of identifying an $\varepsilon$-best arm vanishes. In this setting, we show a novel instance dependent lower bound. In particular, we show that any family of $(\varepsilon,\delta)$-PAC algorithms must incur an expected cumulative regret up to the stopping time that scales as $\log(1/\delta)$, with an instance-dependent constant $C(\mu)$. This is proved using a novel regret-aware change-of-measure technique that allocates information given a budget on the regret. To achieve this lower bound, we devise an algorithm, \algname, that achieves the same scaling in $\delta$, i.e., $\log (1/\delta)$, but with a different constant, which we call $C^\*(\mu)$. KL-UCB+Greedy has two main benefits: (i) it is computationally efficient as $C^\*(\mu)$ admits a closed-form expression; (ii) in broad classes of reward distributions such as Gaussian distributions, $C^\*( \mu) = C( \mu)$, demonstrating asymptotic optimality of KL-UCB+Greedy within these classes. As auxiliary results, we also derive lower bounds on the sample complexity of any family of $(\varepsilon,\delta)$-algorithms as $\delta$ vanishes and show that the sample complexity of KL-UCB+Greedy closely matches that of the lower bound on the sample complexity.

Omnimodal large language models (OmniLLMs) have recently gained increasing attention for unified audio-video understanding. However, processing long multimodal token sequences introduces substantial computational overhead, making efficient token compression crucial. Existing methods typically rely on fixed, modality-specific guidance, which fails to account for the varying importance of modalities across different queries. To address this limitation, we propose $\textbf{OmniSelect}$, a training-free, modality-adaptive token pruning framework that dynamically selects appropriate compression strategies for multimodal inputs. Specifically, we leverage a lightweight AudioCLIP model to estimate cross-modal relevance and categorize each input into three pruning regimes: Audio-Centric, Video-Centric, and Uniform pruning. Based on these relevance scores, OmniSelect further performs fine-grained token pruning within each temporal group, adaptively allocating pruning ratios to preserve informative tokens across modalities. By explicitly modeling modality preference and enabling dynamic strategy selection, OmniSelect effectively avoids the pitfalls of one-size-fits-all compression. Extensive experiments demonstrate that our method achieves efficient multimodal token reduction while maintaining strong performance, without requiring any additional training.

Reinforcement learning with verifiable rewards has made post-training effective when correctness can be verified automatically, but many useful model behaviors require satisfying several qualitative criteria rather than a single verifier. Rubric-based rewards extend RLVR to these open-ended domains by grading prompt-specific criteria and aggregating them into a scalar reward. However, the common static aggregations conflate a criterion's desired end-state importance with its current usefulness for learning. We show that this conflation is central in rubric RL: many criteria that matter to the final answer are already saturated or currently unreachable for the policy, while criteria with informative rollout variation are not reliably the ones assigned the largest human weights. We introduce a Policy-Aware Rubric Reward framework for RLVR, \textbf{POW3R}, that keeps human weights and reward category balance as the target objective while reallocating within-category training pressure toward criteria that distinguish the current rollouts. Across three base policies on each of two datasets spanning multimodal and text-only settings, POW3R takes first place on $27$ of $33$ (base policy, metric) cells we evaluate, leading both mean rubric reward and the harder strict ``every-rubric-passed'' pass-rate over vanilla GRPO with rubric-based rewards, and reaches the same plateau in $3$--$4\times$ fewer training steps. These findings suggest that rubric rewards should separate what should matter in the final answer from what can teach the current policy.

Multimodal heterogeneous learning aims to train reliable multimodal models when data sources differ in modality availability, semantic coverage, domain distribution, and missingness patterns. Although cross-modal alignment is widely used to mitigate such heterogeneity, we argue that alignment is not free: enforcing relations that are weakly supported by the observed data can amplify noise, over-transfer missing-modality information, and induce negative transfer. This paper studies when a modality--modality--semantic relation is sufficiently observable to be safely aligned and shared across heterogeneous sources. We propose **ObsAlign**, an observability-aware framework that summarizes visible modality--semantic evidence through compact source-level sketches and estimates relation-level support from bridge evidence, side support, cross-modal consistency, and prototype uncertainty. The resulting observability score gates co-observed alignment, calibrates weak missing-modality transfer, and guides evidence-aware source consolidation so that reliable relations are shared while unsupported variation remains local. Across image--text, audio--visual--text, action-recognition, sensor, and healthcare benchmarks under source-partitioned multimodal heterogeneity, ObsAlign achieves the best overall performance in both encoder-based and VLM-compatible regimes, while sharply reducing negative transfer on low-observability relations. These results suggest that relation-level observability provides a practical principle for deciding when cross-modal alignment should be strengthened, weakened, or avoided.

We investigate the **strategic surplus** obtainable against a **Follow-the-Regularized-Leader (FTRL)** learner with constant step size $\eta$ in $n \times m$ two-player zero-sum games played over $T$ rounds against a clairvoyant optimizer. In contrast with prior analysis, we show that the extraction of such regret-scale surplus is an inherent feature of the FTRL family, rather than an artifact of specific instantiations. First, for a fixed max-min optimizer, we establish a sweeping law of order $\Omega(N/\eta)$, proving that utility surplus scales with the number of the learner's suboptimal actions $N$ and vanishes in their absence. Second, for an alternating optimizer, a surplus of $\Omega(\eta T/\text{poly}(n,m))$ can be guaranteed regardless of the equilibrium structure, with high probability, in random games. Our analysis uncovers a sharp geometric dichotomy: **non-steep** regularizers allow the optimizer to realize the maximal transient surplus via finite-time elimination of suboptimal actions, whereas **steep** regularizers introduce a vanishing tail correction that can delay surplus saturation. Finally, we discuss whether this leverage persists under bilateral payoff uncertainty and propose a susceptibility measure quantifying which regularizers are most vulnerable to learner-aware strategic steering.

Dynamic graph learning models the temporal evolution of structural interactions. Existing methods present a stark trade-off between performance and efficiency. Event-based models achieve strong accuracy because processing graphs edge-by-edge allows them to continuously update and leverage fine-grained joint neighborhood information. Conversely, snapshot-based methods offer high computational efficiency by processing entire snapshots simultaneously. However, updating neighborhood states for all nodes concurrently is computationally prohibitive. Consequently, current snapshot methods fail to utilize joint neighborhood information, leading to significantly weaker performance. To bridge this gap, we propose the Neighbor-Aware Graph Neural Network (NAGNN), a novel snapshot-based architecture that seamlessly integrates joint neighborhood information to achieve both strong performance and high efficiency. Specifically, NAGNN introduces a Locality-Sensitive Hashing (LSH)-based topology distiller to construct compact reservoirs that store neighborhood information efficiently. These reservoirs are further augmented with degree-scaled statistical moments to encode structural characteristics of local neighborhoods. A Gated Recurrent Unit (GRU) subsequently processes the distilled structural representations to model and capture their temporal dynamics. Extensive experiments demonstrate that NAGNN matches the predictive accuracy of computationally expensive event-based models with minimal overhead, establishing a highly scalable and effective paradigm for dynamic graph learning.

Different optimizers impose different geometries on parameter updates. Adaptive methods such as Adam and AdamW use coordinate-wise updates, while matrix-aware optimizers such as Muon utilize weight-matrix structure through orthogonalized updates. For Graph Neural Networks (GNNs), however, the effective geometry of its weight matrices is shaped not only by its learned channel-mixing weights, but also by the graph-propagated representations it acts on. Thus, even if an update is well normalized as a matrix, its effect on the layer output can be amplified when applied to graph-propagated features. To address this gap, we introduce GraphMuon, a graph-aware optimizer that adapts Muon's matrix updates to the covariance structure of graph-propagated layer inputs. GraphMuon performs orthogonalization in a metric defined by these propagated representations and normalizes step sizes according to the update's induced effect on the layer representation. We show that theoretically, vanilla Muon can suffer from graph-induced update amplification, while our GraphMuon can mitigate this effect. As such, our GraphMuon yields a graph-metric analogue of Muon's polar update step. Empirically, we show that GraphMuon achieves $2.13\times$-$7.38\times$ speedups in time-to-target wall-clock runtime over AdamW across diverse graph-learning regimes, while maintaining competitive or superior predictive performance.

Large Language Models (LLMs) are trained to support an increasing number of languages, yet their predefined tokenizers remain a bottleneck for adapting models to lower-resource or distinct-script languages. Existing tokenizer transfer methods typically rely on semantic heuristics to initialize new embeddings, ignoring higher-layer model dynamics and limiting transfer quality. We propose Model-Aware Tokenizer Transfer (MATT), a method that incorporates model internals into the tokenizer transfer process. MATT introduces an Attention Influence Modeling (AIM) objective that distills inter-token communication patterns from a source model into a target model with a new tokenizer, providing an efficient warm-up before standard language modeling. Unlike approaches that focus solely on embedding similarity, MATT leverages attention behavior to guide embedding initialization and adaptation. Experiments across diverse linguistic settings show that MATT recovers a large fraction of the original model’s performance within a few GPU hours, outperforming heuristic baselines. These results demonstrate that incorporating model-level signals offers a practical and effective path toward robust tokenizer transfer in multilingual LLMs.

Multimodal dataset distillation (MDD) seeks to synthesize compact surrogates from large-scale image-text corpora, reducing the high cost of pre-training. Although recent feature-matching methods have improved the efficiency of MDD, they often suffer from initialization overfitting, which distorts the cross-modal structure and severely degrades retrieval performance under unseen initializations. To mitigate this issue, we propose $\textbf{MDA-DD}$, which enhances generalization via a dynamic staggered model queue. We further identify two architectural bottlenecks in prior work: structurally redundant projections and inefficient covariance computation. For the former, we design an asymmetric dual projection to reduce redundancy while preserving balanced bidirectional cross-modal alignment. For the latter, we introduce a Second-Order Cross-Modal Moment (SOCM) objective, which efficiently captures both mean and correlation statistics across modalities. Experiments on Flickr30K and MS-COCO show that $\textbf{MDA-DD}$ consistently surpasses existing methods, yielding notable retrieval improvements (e.g., +12.9 IR@1 and +18.2 TR@1 in the 100-pair setting) and matching or exceeding baselines trained on 500 pairs using only 100 pairs.

LLM post-training is usually framed as a choice of optimizer, but KL-regularized RL also makes a hidden geometric choice: it fits the learned policy to a reward-tilted target by reverse KL. This places PPO, GRPO, RLOO, REINFORCE++, and related methods at a fixed mode-seeking point in a broader design space. We propose \textbf{Mode-Controlled Policy Optimization (MCPO)}, a geometry-aware recipe that replaces this inherited point with an $\alpha$-divergence dial over mode-seeking versus mode-covering behavior; $\alpha{=}0$ recovers the classical reverse-KL recipe. MCPO admits an off-policy objective, a practical grouped importance-weighted estimator, and a baseline-centered variant for stable training. Across mathematical reasoning, agentic transfer, search-based QA, and safety, no single geometry is uniformly best. Average-case math favors stronger concentration, while pass-based math and Search-QA favor broader support; agentic transfer moves with metric and scale; safety exposes a base-dependent frontier in which the same refusal-only signal can transfer broadly or spill into benign boundary cases depending on the reference model's mode landscape. MCPO's value is therefore not a new universal objective, but a way to expose and select the post-training geometry that RL with fixed reverse-KL geometry silently chooses.

Mixture-of-Experts (MoE) enables multimodal large language models (MLLMs) to scale capacity efficiently, but expert parameters dominate memory—accounting for over 90% of model size in modern MoE-MLLMs (e.g., 54 GB out of ∼58 GB in BF16 for InternVL3.5-30B-A3B and Qwen3-VL-30B-A3B)—even though only a few experts are activated per token. Expert pruning has emerged as an effective compression strategy, but existing methods aggregate importance uniformly across tokens, ignoring that the same expert may serve different roles for vision versus language processing. To address this, we propose MAEP (Modality-Aware Expert Pruning), a training-free framework that decomposes expert importance by modality in a single forward pass. MAEP introduces (1) Delta-H Output (∆H), a redistribution-aware metric measuring the MoE output change when an expert is removed, and (2) low-attention vision tokens as a vision-side pruning signal that is dataset-stable: its expert-importance ranking remains stable across different datasets. Text-side importance serves as a preservation signal while vision-side importance serves as a pruning signal, and experts are ranked globally across layers. Experiments on three MoE-based MLLMs across multimodal and text benchmarks show that MAEP outperforms modality-agnostic baselines on the majority of multimodal benchmarks while remaining competitive on text-only tasks, reducing the BF16 expert weight footprint by ∼27 GB (∼47% of total memory) so that the expert-weight footprint fits within a single 40 GB GPU.

3D visual grounding (3DVG) localizes language-referred objects in 3D scenes, with broad applicability in both indoor and outdoor environments. However, existing 3DVG research focuses on static indoor objects, limiting its use in dynamic outdoor autonomous driving. Motion descriptions, which capture the temporal dynamics of moving objects, offer a promising way to address this challenge. We therefore introduce MoT3DVG, a large-scale dataset for dynamic-aware outdoor 3DVG with temporally evolving motion descriptions. It contains 850 scenarios with 31,128 frames from nuScenes dataset, and provides 144,568 language prompts with motion-aware descriptions for dynamic objects across time. We further propose DynaVG, a novel framework that effectively leverages temporal cues for outdoor 3DVG. In addition to the standard modality-specific encoders, DynaVG introduces a Short-Long Integrated Dynamic Encoding (SLIDE) module before the language-point cloud alignment. SLIDE models both local motion cues and global temporal context via short-term window encoding and long-term window shifting. Extensive experiments demonstrate its state-of-the-art performance on MoT3DVG, validating the effectiveness of motion-aware encoding. Our work reveals open challenges and promising directions for future research in outdoor 3DVG.

Scaling large language models efficiently has motivated sparse capacity mechanisms such as Mixture-of-Experts and, more recently, conditional memory: token-indexed embedding tables that augment the backbone with cheap parametric lookups. Existing memory-embedding methods retrieve via a deterministic function of the surface form, which collapses different contextual senses of the same token (\eg, \emph{python} the language vs.\ the animal) into a single fixed entry. We introduce Mixture of Memory Embeddings (MoME), a context-aware memory mechanism that replaces each token's single memory row with a mixture of $M$ slots and uses a learned gate over the hidden state to choose which slots to read at each position. In controlled pretraining experiments across nanochat, Llama-3/MobileLLM, and Qwen3 backbones from $125$M to $0.6$B parameters, MoME consistently outperforms Value Embedding, Engram, and STEM baselines at matched memory \& training budgets, shows a more favorable memory-size scaling trend than Engram on the nanochat backbone, and remains compatible with Engram-style memory under compound scaling. Qualitative routing analyses on polysemous tokens further suggest that the learned mixture exhibits a degree of semantic interpretability, dispatching the same surface token to distinct memory slots under different senses rather than collapsing them into a single fixed entry. All Code and model checkpoint will be open sourced.

Speech large language models (SLMs) are typically built from text large language model (TLM) checkpoints, yet they still suffer from a substantial modality gap. Prior work has mainly attempted to reduce this gap from the output side by making speech generation more text-like, but the gap remains. We argue that the key remaining bottleneck lies on the input side. We propose TextPro-SLM, an SLM that makes spoken input more closely resemble that of a prosody-aware text LLM. TextPro-SLM combines WhisperPro, a unified speech encoder that produces synchronized text tokens and prosody embeddings, with an LLM backbone trained to preserve the semantic capabilities of the original TLM while learning paralinguistic understanding. Experiments show that TextPro-SLM achieves the lowest modality gap among leading SLMs at both 3B and 7B scales, while also delivering strong overall performance on paralinguistic understanding tasks. These gains are achieved with only roughly 1,000 hours of audio training data, suggesting that reducing the modality gap from the input side is both effective and data-efficient.

This position paper argues that AI for mental health must move beyond two dominant paradigms. The first is diagnostic prediction, which frames mental healthcare as symptom detection, diagnosis, and decision-making. The second is chat-based support, which reduces therapeutic interaction to language-mediated information delivery. Both approaches neglect what therapeutic research shows to be central to healing: experiential, affective, and embodied processes. In many therapeutic traditions, insight emerges not through information-delivery but through emotionally resonant, multisensory experiences that allow individuals to feel, reflect, and reframe their inner world. We propose an alternative framework: co-experiential AI systems that identify emotionally salient moments across modalities, modulate sensory experience to facilitate reflection, and adapt over time to a user's evolving responses and interpretations. Using dreamwork therapy as a stress test for mental health AI, we define three key challenges for AI systems: identifying affective anchors in indeterminate multimodal interactions; modeling user perspective as a situated context; and enabling continual adaptation to individuals without repeated retraining. We posit that addressing these challenges requires rethinking AI's role not as an expert, but as a perspective-aware participant in human meaning-making.

Unit-modulus measurement vectors, due to their phase-only variations, exhibit favorable hardware compatibility and storage efficiency. In this paper, we consider matrix recovery using symmetric unit-modulus rank-one measurements. We identify a fundamental limitation of symmetric unit-modulus measurements---their inability to capture individual diagonal entries, and show that matrix recovery can be achieved using such measurements when the diagonal entries are known or directly measurable. We construct a stacked operator and establish that it satisfies a mixed-norm restricted isometry property ($\mathrm{mRIP}$) for unit-modulus measurements. Leveraging the $\mathrm{mRIP}$ condition, we derive exact and stable recovery results for matrix recovery with unit-modulus measurements in both noiseless and noisy settings. Our work is the first to provide the theoretical foundation for matrix recovery under symmetric rank-one unit-modulus measurements. Numerical experiments further corroborate these theoretical findings.

The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking methods have been proposed to embed identifiable multi-bit messages into generated text for misuse tracing. However, existing methods often suffer from a fundamental trade-off between text quality and decoding accuracy. In particular, they have to restrict the size of the preferred token set (i.e., green list) during encoding to maintain a detectable watermark signal for decoding, which inevitably degrades generation quality. To improve this trade-off, we propose a novel message encoding paradigm called \textit{majority bit-aware encoding}, which relaxes the watermark signal strength from the green list size. This strategy allows for a strong watermark signal to be preserved in generated texts even when using a large green list. We introduce two instantiations of this paradigm: MajorMark and MajorMark$^{+}$, where the latter is specifically optimized for long messages. Extensive experiments on state-of-the-art LLMs demonstrate that our methods achieve higher decoding accuracy and superior text quality compared to prior baselines. The code of the proposed methods is available \href{https://anonymous.4open.science/r/MajorMark}{here} for review.

Multi-objective Bayesian optimization (MOBO) traditionally aims to approximate the entire Pareto front, but real-world deployment is often limited to a small, representative subset of solutions due to resource constraints. Current two-stage methods first approximate the full front before selecting solutions, wasting evaluation budget. We formalize this problem as Multi-objective Bayesian Optimization with Cardinality-aware Pareto Selection (MOBO-CAPS), where the goal is to identify a set of exactly $M$ solutions with high hypervolume. We propose two practical cardinality-aware acquisition strategies: REHVI, a replacement-aware approximation to expected hypervolume improvement, and CHO-UCB, which constructs an optimistic $M$-point set by optimizing a collective UCB-based hypervolume objective. We prove a sublinear simple regret bound for the batched version of CHO-UCB, and empirically show that cardinality-aware acquisition design improves over standard MOBO followed by post-hoc subset selection across nine benchmarks.

Direct Preference Optimization (DPO) has become a popular route for aligning large language models with human preferences, but existing pipelines treat all preference pairs uniformly and ignore prompt-level heterogeneity. We show that the optimal pair-selection strategy varies systematically with prompt characteristics: prompts with concentrated reward distributions benefit from large reward-gap pairs that provide unambiguous signal, while prompts with diverse responses benefit from moderate-gap pairs because extreme positions are dominated by outliers. No fixed strategy is optimal across this heterogeneity. We propose META-PAP (Meta-learning for Prompt-aware Preference Pairing), a framework that turns this observation into a learned algorithm. META-PAP generates multiple diverse pairs per prompt via a structured grid over the response reward distribution, extracts a compact prompt-aware feature vector, and trains a lightweight meta-network through bilevel optimization to predict per-pair weights. The inner loop is a weighted DPO update; the outer loop evaluates a virtual policy on a small clean meta-set. Across Llama-3-8B, Mistral-7B-v0.3, and Llama-2-7B, META-PAP consistently outperforms vanilla DPO, fixed-position pairing, reward-gap weighting, top-$k$ filtering, curriculum, and statistical rejection sampling, with average gains of $+3.9$ points on AlpacaEval~2.0 and $+3.2$ points on Arena-Hard, and approaches an oracle that exhaustively searches per prompt. The learned weighting policy is interpretable: it favors large-gap pairs on low-diversity prompts and softly rejects extreme pairs on high-diversity prompts. We additionally find that the meta-network requires only $M\!=\!150$ pairs to saturate, transfers across domains, tolerates label noise on the meta-set, and remains effective with as few as $n\!=\!32$ on-policy samples per prompt.