NeurIPS 2026 论文列表

Existing semi-supervised adversarial training (SSAT) methods typically employ a teacher-student framework where a teacher model provides supervisory signals for unlabeled data. However, they rely on static supervision---either hard pseudo-labels or soft labels with fixed temperature---which maintains constant learning difficulty throughout training. This rigidity fails to accommodate the student's evolving capability, especially when the teacher's performance plateaus. To address this, we reframe SSAT as knowledge distillation from a Bayes teacher and formalize a stage-dependent bias-variance tradeoff. This analysis reveals the existence of an optimal temperature: low temperatures reduce bias, while higher temperatures control the variance term in the robust generalization bound. Guided by this insight, we propose BayesAT, a Bayes-guided progressive distillation framework that jointly employs a low-to-high temperature warming schedule and confidence-adaptive sample reweighting. BayesAT allows the student to first learn from sharp, high-confidence supervision to establish reliable decision boundaries, then progressively from smoother distributions that encourage exploration of inter-class relationships. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet-200 demonstrate that BayesAT consistently improves robust accuracy while maintaining natural accuracy over existing SSAT methods, highlighting the importance of dynamic, theory-driven supervision for effective knowledge transfer in semi-supervised adversarial training.

Executable world models can be read, edited, executed, and reused for planning, but only if the program captures the environment's transition law rather than semantic shortcuts in its surface vocabulary. We study online executable world-model learning under prior misalignment, where an agent must induce state-dependent dynamics from interaction evidence alone, without rule descriptions, reward signals, or trustworthy lexical priors. We introduce Alice, a closed-loop system that treats failed candidate updates as structural signal: when a candidate explains a new transition but loses previously explained ones, the preservation conflict reveals dynamics that the current program had conflated. Alice refines these conflicts into hypothesis classes that both provide compact, class-stratified preservation counterexamples for update and guide frontier exploration toward transitions that are novel and underrepresented with respect to the current program. We evaluate Alice on Baba in Wonderland, a prior-misaligned variant of Baba Is You that preserves simulator dynamics while replacing semantically meaningful rule-property labels with unrelated words. Experiments show that Alice substantially improves executable world-model learning under prior misalignment, and ablations show that both class refinement and class-aware exploration contribute.

Self-Driving Chemical Laboratories (SDCLs) are moving chemical experimentation toward embodied automation, where machines must perceive laboratory scenes, reason about experimental states, and act under physical, procedural, and safety constraints. Although Multimodal Large Language Models (MLLMs) are increasingly considered as embodied brains for such systems, existing laboratory benchmarks mainly focus on safety, anomaly detection, or general scientific understanding, leaving their execution-oriented embodied capabilities underexplored. To fill this gap, we introduce BEAKER, a Benchmark for evaluating Embodied Actionability, Knowledge, Experimentation, and Reasoning in SDCLs. BEAKER contains 1,000 expert-curated QA samples across 11 image and video task types, covering key judgments required for chemical laboratory execution, including affordance grounding, trajectory planning, equipment and state understanding, apparatus connection, operation process reasoning, and result understanding. All questions and annotations are manually created and reviewed by chemistry and embodied AI experts, without AI-assisted generation or annotation. We evaluate 28 general-purpose, scientific, chemical, and embodied MLLMs on BEAKER. Results show that current models can recognize laboratory objects and states, but still struggle to ground experimental knowledge into operable regions, feasible trajectories, and long-horizon procedural reasoning. BEAKER thus reveals a clear gap between multimodal laboratory perception and action-grounded experimental understanding, providing a diagnostic benchmark for future MLLMs in SDCLs.

Modern transformation-aware self-supervised representations are routinely scored under protocols that grant the evaluator paired views, augmentation labels, or teacher anchors --- none of which the deployed predictor ever sees. We audit the gap that opens once these privileges are removed and only a single query remains. The finding is a systematic evaluation illusion: on 3DIEBench-Honest, honest single-query rotation errors are typically $2{-}3\times$ as large as native transformation scores, consistently across comparators and matched-utility thresholds. To make this gap measurable, we introduce a deployment-honest evaluation contract specifying a one-query test interface, matched semantic utility, a strongest-eligible-neighbor headline with tail summaries, and explicit privilege accounting. Theory and experiments are in service of the contract: lower-bound analysis grounds the contract at the interface level, while a positive control supplies a non-vacuous upper certificate under declared privileges. We exercise the contract on a generated law, on 3DIEBench-Honest, and on PTB-XL. The operational conclusion is that native transformation-aware success is not, on its own, a single-query deployment certificate.

Recent audio embedding models learn general-purpose representations that transfer across clip- and frame-level tasks, yet they operate almost exclusively on single-channel signals and are blind to spatial structure. Spatial audio models capture that structure but rely on clip-level supervision or contrastive objectives, yielding embeddings unsuitable for frame-level tasks like sound event detection and localization (SELD). We argue this dichotomy is not fundamental: patch-level spatial self-supervision can jointly learn acoustic and spatial features at both temporal granularities. We introduce AudioSphere, a multi-channel masked autoencoder trained on Ambisonics recordings that reconstructs both spectral content and directional cues via a joint spatiotemporal masking strategy that masks both time-frequency patches and intensity vectors. AudioSphere supports frame-level predictions while producing strong clip-level representations via aggregation. Alongside the model, we release RealSELD, a standardized benchmark for evaluating frozen backbones on real-world multi-channel SELD. AudioSphere enables, for the first time, SELD with a frozen self-supervised backbone, while matching or exceeding prior general-purpose audio embedding models on the HEAR benchmark.

Robust visual classification often depends on localizing the main foreground objects in an image while ignoring spatially-separable distractors. Surprisingly, we find that the attention maps of smaller self-supervised ViTs localize foreground objects better than those of larger ones. However, we still need large ViTs, because they extract richer representations from each patch. To get the best of both worlds, good localization _and_ rich representations, we propose $A^2$, a simple method that leverages this inverse scaling finding by decoupling _where to look_ (a small attention model) from _what to extract_ (a large embedding model): we crop around the attention peaks of a small model and embed the crops with a larger model. $A^2$ uses entirely pretrained features and does not require per-dataset attention or backbone training. Across $5$ benchmarks, $A^2$ is competitive with backbone-matched loss-level methods like DFR, and outperforms end-to-end attention training under stronger distribution shifts.

Partial Label Learning (PLL) trains models from instances with candidate label sets containing the ground-truth, while Semi-Supervised Partial Label Learning (SSPLL) further leverages the available unlabeled data to prompt the performance. The previous SSPLL methods implicitly assume the unlabeled data are class-balanced distributed. However, in realistic scenarios, the class distribution of unlabeled data is unknown, resulting in performance collapse on minority classes for the existing SSPLL methods. We identify two coupled biases behind this failure: (i) pseudo-label selection bias, where high-confidence filtering tends to over-select samples from dominant classes, causing the training data to become increasingly skewed toward these classes; and (ii) disambiguation bias, where dominant classes are more likely to win within candidate sets, even when they are incorrect. Theoretically, we show that these two biases reinforce each other over training, forming a feedback loop that degrades generalization performance. To weaken this loop, we propose AdapMatch, which uses DAS to reduce the skew in training data caused by pseudo-label selection bias via prior-aware pseudo-label admission and CAD to lower the disambiguation error by suppressing candidate-set domination. Across five benchmarks, AdapMatch yields gains up to 41.31\% at most , showing strong robustness to varying scale, imbalance, and ambiguity. The code is available at \url{https://anonymous.4open.science/r/AdapMatch-8BC5}.

Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns an embodied policy from unlabeled, noisy internet video, without reward shaping or expert annotation. ASH follows a self-improvement loop; when it gets stuck, ASH learns an Inverse Dynamics Model (IDM) from its own trajectories, and uses its IDM to extract supervision from relevant internet video. ASH uses unsupervised learning to identify key moments from large-scale internet video and retains them as long-term memory --- allowing it to tackle long-horizon problems. We evaluate ASH on two complementary environments demanding multi-hour planning: Pokemon Emerald, a turn-based RPG, and The Legend of Zelda: The Minish Cap, a real-time action-adventure game. In both games, behavioral cloning, retrieval-augmented and zero-shot foundation-model baselines plateau, while ASH sustains progression across our 8-hour evaluation. ASH reaches an average of $11.2/12$ milestones in Pokemon Emerald and $9.9/12$ in Legend of Zelda, while the strongest baseline gets stuck in both environments at an average of $6.5/12$ and $6.0/12$ milestones, respectively. We demonstrate that self-improving agents are a scalable recipe for long-horizon embodied learning.

3D Gaussian Splatting (3DGS) has become a vital tool in novel view synthesis. 3D Gaussian functions with attributes like color, opacity, and scale are stacked together to explicitly model a radiance field. However, discrete 3D Gaussians usually produce poor depth with few geometry details but lots of floaters, which makes modeling smooth radiance fields remain a challenge. To address this issue, we propose to learn a radiance field within a continuous view-dependent color field parameterized by neural networks. With the continuous constraints in color, the bias on low-frequency signals of neural networks highly encourages the geometry to contribute to high-frequency color variations on images, but not solely relying on the color attribute itself. Moreover, we impose a constraint to improve the Lipschitz continuity of the neural color field, making large changes of each Gaussian's color also match with large changes of its position in terms of a ratio. To this end, we additionally introduce novel self-learning strategies to learn neural view-dependent color fields without any external knowledge or priors, aiming for better generalization. Our numerical and visual comparisons on widely used benchmarks justify our idea and show better ability of high fidelity geometry recovery in 3DGS.