NeurIPS 2026 论文列表

Building humanoid robots that perform generalizable whole-body loco-manipulation in the real world remains a fundamental challenge: existing approaches either rely on heavy task-specific reward engineering, rigidly replay reference motions that fail to generalize, or depend on costly teleoperation that limits scalability. While human videos capture diverse human behaviors, the motion priors inferred from them are inherently imperfect, suffering from occlusion, contact artifacts, and retargeting errors that render them unsuitable for direct policy learning. To this end, we present SUGAR, a data-driven framework that converts diverse human videos into deployable humanoid loco-manipulation skills, without any task-specific reward engineering or reference-motion conditioning at inference. SUGAR proceeds in three coupled stages: First, a fully automated pipeline extracts scalable kinematic interaction priors including human-object motion trajectories and contact labels from diverse human videos. Second, a privileged physics-based refiner utilizes a unified mimic-style reward and a progressive state pool to transform imperfect kinematic interaction priors into physically feasible, high-fidelity skills. Third, the refined skills are distilled into a hierarchical policy that comprises a task-guided planner and a command tracker for autonomous task execution. We evaluate our method on six representative loco-manipulation tasks in both simulation and real-world humanoid hardware. SUGAR substantially outperforms reference-tracking baselines, and its performance scales clearly with the amount of human video data. It also achieves zero-shot real-world transfer with reliable closed-loop execution, autonomous failure recovery and stable long-horizon performance under external perturbations. Project Page: https://sugar-humanoid.github.io/

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain coverage, while scalar scores further impose an information bottleneck, offering insufficient semantic bandwidth to improve intermediate decisions. Alternative language-critique approaches, which rely on frozen or external critics, provide richer textual feedback but lack the scalability needed for sustained policy improvement. In this work, we propose language-driven stepwise trajectory redirection, termed as **STRIDE**, a novel training framework that shifts process supervision from scalar rewards to *learnable* stepwise language feedback. Specifically, we co-train a generator and a generative verifier using only outcome-based rewards, eliminating external annotations, while delivering sustained policy improvement through jointly aligned verifier training. The verifier's stepwise language critiques explicitly localize and explain failures, enabling the generator to redirect reasoning trajectories at intermediate steps toward alternative decisions. The trajectory redirection design guarantees harmless policy improvement, even under noisy or suboptimal verifier feedback. Experiments on diverse reasoning benchmarks show that STRIDE significantly outperforms state-of-the-art baselines, as well as achieving breakthroughs on zero-pass-rate problems where scalar methods yield no learning signal in our ablation studies, demonstrating the effectiveness of learnable stepwise language feedback for enhancing LLM reasoning.

Benchmarking tabular learning has revealed the benefit of dedicated architectures, pushing the state of the art. But real-world tables often contain string entries, beyond numbers, and these settings have been understudied due to a lack of a solid benchmarking suite. They lead to new research questions: Are dedicated learners needed, with end-to-end modeling of strings and numbers? Or does it suffice to encode strings as numbers, as with a categorical encoding? And if so, do the resulting tables resemble numerical tabular data, calling for the same learners? To enable these studies, we contribute STRABLE, a benchmarking corpus of 108 tables, all real-world learning problems with strings and numbers across diverse application fields. We run the first large-scale empirical study of tabular learning with strings, evaluating 445 pipelines. These pipelines span end-to-end architectures and modular pipelines, where strings are first encoded, then post-processed, and finally passed to a tabular learner. We find that, because most tables in the wild are categorical-dominant, advanced tabular learners paired with simple string embeddings achieve good predictions at low computational cost. On free-text-dominant tables, large LLM encoders become competitive. Their performance also appears sensitive to post-processing, with differences across LLM families. Finally, we show that STRABLE is a good set of tables to study “string tabular” learning as it leads to generalizable pipeline rankings that are close to the oracle rankings. We thus establish STRABLE as a foundation for research on tabular learning with strings, an important yet understudied area.

Automatically migrating serial C programs to parallel CUDA is essential for high-performance computing, yet remains challenging due to the partial observability of data dependencies: critical memory access patterns cannot be reliably inferred from source code alone. Existing static analysis methods often fail on irregular and pointer-intensive loops, while LLM-based approaches cannot infer memory-access-dependent optimization strategies from source text alone. To address these limitations, we propose STParOpt, which formulates parallelism and optimization inference as an uncertainty-aware learning problem under partial observability, where ambiguity in static analysis is explicitly quantified and resolved using execution signals. STParOpt augments static program graphs with stride-level execution features via cross-attention, and employs an entropy-guided fusion mechanism that up-weights dynamic evidence when the static branch's predictive entropy over parallelizability is high. Experiments on standard HPC benchmarks demonstrate that STParOpt significantly outperforms both compiler-based and LLM-based baselines on parallelism detection and CUDA code generation. Notably, STParOpt achieves 96.4% parallelism detection accuracy and 86.1% end-to-end generation correctness, surpassing the strongest baseline by +5.0 pp and +11.4 pp respectively.

We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised contrastive objective to learn a low-dimensional latent space where progression manifests along manifolds anchored by fixed prototype vectors. This structure yields latent-space indicators that quantify progression in a human-meaningful way without proxy labels. We evaluate the approach against the state of the art on diverse domains, including industrial degradation, robotic tasks, and neural activity, validating three key capabilities: (1) end-state prediction, (2) multi-step forecasting, and (3) interpretable phase separation. Our method matches or improves over black-box counterparts on all of these while providing transparency about the underlying mechanisms. A simple linear regressor on top of the learned indicators is competitive with deep architectures, providing direct quantitative evidence that the underlying state is encoded in a geometrically accessible form. Code is available at https://anonymous.4open.science/r/LRPTS-9300/README.md.

Vision-language action (VLA) models excel for end-to-end autonomous driving, yet their tendency to over-invoke chain-of-thought (CoT) reasoning mirrors a human cognitive pitfall: overthinking. Just as deliberate reasoning can slow/mislead human judgment in routine tasks, excessive CoT in VLA incurs unnecessary compute overhead and can paradoxically degrade planning performance. Recent research tackles this via adaptive reasoning, which dynamically modulates inference complexity by selectively triggering CoT for complex scenes while responding directly to routine ones. While prior adaptive methods rely on implicit adaptation, recent work shows that explicitly optimizing the route between CoT and direct responses yields superior performance, assuming scene-difficulty annotations which are labor-intensive, poorly scalable, and prone to error due to the subjectivity of judging driving complexity. We explore, for the first time, whether adaptive reasoning with explicit route optimization can be achieved without any scene-difficulty labeling. We introduce STEER, a generic over-reasoning mitigation strategy featuring two key components: (i) routing uncertainty-aware rollout, which calibrates sampling to align routing diversity with model uncertainty; and (ii) cross-route advantage credit assignment, which introduces a differential metric to reinforce optimal routing decisions based on environmental rewards rather than subjective labels. Extensive experiments on NAVSIM v1/v2 demonstrate state-of-the-art results in both planning quality and the Pareto front of inference efficiency.

Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training. We conduct a first-order gradient analysis of token-level entropy dynamics under GRPO and identify a token-level credit assignment mismatch: the per-token entropy variation decomposes into the product of the trajectory-level advantage and an entropy sensitivity function over the next-token distribution, yielding an advantage-surprisal four-quadrant structure and a near-criticality property. Motivated by it, we propose STARE (Surprisal-guided Token-level Advantage Reweighting for policy Entropy stability), which identifies entropy-critical token subsets via batch-internal surprisal quantiles, selectively reweights their effective advantages, and incorporates a target-entropy closed-loop gate for stable entropy regulation. Across model scales from 1.5B to 32B and three task families (Short CoT, Long CoT, and Multi-Turn Tool Use), STARE sustains stable RL training over thousands of steps while maintaining policy entropy within the target band. On AIME24 and AIME25, STARE outperforms DAPO and other competitive baselines by 4%–8% in average accuracy, with reflection tokens and response length growing in tandem, indicating sustained exploration–exploitation balance that further unlocks RL training potential.

Existing Time Series Foundation Models (TSFMs) for Multivariate Time Series Anomaly Detection often overlook discrete *state variables* that describe system status and treat them uniformly with *numerical variables*. This inappropriate modeling approach prevents the model from fully leveraging state information and even leads to significant performance degradation when state variables are integrated. To address this limitation, this paper proposes a novel **ST**ate-aware **A**dapte**R** (STAR). Specifically, STAR comprises three core innovative components: (1) an *Identity-guided State Encoder* that effectively captures the complex semantics of state variables; (2) a *Conditional Bottleneck Adapter* that dynamically injects state influence into TSFMs; and (3) a *Numeral-State Matching* module that effectively detects anomalies inherent to the state variables themselves. Extensive experiments on real-world datasets demonstrate that STAR significantly improves the performance of existing TSFMs.

Reinforcement Learning (RL) has significantly improved large language model reasoning, but existing RL fine-tuning methods rely heavily on heuristic techniques such as entropy regularization and reweighting to maintain stability. In practice, they often suffer from late-stage performance collapse, leading to degraded reasoning quality and unstable training. We identify a key factor behind this instability: a small fraction of tokens, termed spurious tokens (around 0.01\%), which contribute little to the reasoning outcome but receive disproportionately amplified gradient updates due to inheriting the full sequence-level reward. We present a unified framework for evaluating token-level optimization impacts across spurious risk, gradient norms, and entropy changes. Building the analysis of token characteristics that severely disrupt optimization, we propose the Silencing Spurious Tokens (S2T) mechanism to efficiently suppress their gradient perturbations. Incorporating this mechanism into a group-based objective, we propose Spurious-Token-Aware Policy Optimization (STAPO), which promotes stable and effective large-scale model refinement. Across six mathematical benchmarks and three model scales, STAPO consistently demonstrates superior entropy stability and achieves average accuracy improvements over baselines including GRPO, 20-Entropy, and JustRL under two widely-adopted evaluation settings.

Training-memory reduction requires identifying which saved tensors drive peak usage and ensuring high-fidelity backward contractions from compressed states. We formalize saved-activation compression as a target-surface prediction problem: a pre-training framework to estimate the replaceable memory surface, computational overhead, and parameter-gradient error. We introduce STAC-R (Subspace Tracked Activation Compression with Residuals), a saved-tensor wrapper storing activations as persistent low-rank coefficients paired with a sparse quantized residual. Weight gradients are contracted directly from these factors, bypassing full decompression. To guide deployment, we propose the Saved-Surface Predictor ($\mathrm{SSP} = A_C^+ / P$), a statistic that upper-bounds peak memory reduction. We also derive a gradient bridge linking reconstruction error to parameter-gradient cosine similarity, determining if a low-precision state preserves update fidelity.Evaluations across GPT-2 (Medium/Large) and Pythia-1.4B pre-training show STAC-R reduces peak memory by 7.2-12.4\% while keeping long-horizon validation perplexity within 1.5\% of baseline (Pythia-1.4B 10k steps: +1.14\%) with mean gradient cosine $\geq$ 0.98. On BERT fine-tuning (SST-2), STAC-R achieves 12.45\% memory reduction with a 0.15pp accuracy decrease. Mechanistic benchmarks yield a mean gradient cosine of 0.9813, outperforming iso-byte SVD (0.9236) and untracked-subspace (0.6949) controls. On the empirical rate-distortion frontier, STAC-R is Pareto-dominant over controls across stored-byte budgets. Composed with GaLore, a "Turbo-fast" variant matches full STAC-R's memory footprint within 0.005 GiB while reaching 0.67𝑥 wall time. Finally, our analysis identifies memory-increasing regimes in SwiGLU architectures (Qwen-2.5/Llama-3.2), establishing STAC-R as a compressor with predictable memory and fidelity conditions checkable before training.

Continual learning suffers from catastrophic forgetting, leading to the loss of past knowledge and unstable adaptation across task streams. Existing approaches typically address this issue through replay buffers, architectural changes, or additional regularization terms. We argue that forgetting is a consequence of unstable learning dynamics, which may benefit from an optimizer-level solution. The main challenge is that learning dynamics are time-dependent, as demonstrated by empirical phenomena such as the stability gap. First, we formally prove that, for distance-based classifiers, bounded parameter drift guarantees bounded margin erosion under a local score-stability condition. Based on this insight, we propose STABLE, a primal–dual optimizer with adaptive drift control. STABLE enforces a drift budget by increasing the dual variable when the budget is violated and decreasing it otherwise. This results in high stability without penalizing plasticity. Experiments on long-horizon unimodal streams and CLIP-based multimodal streams show that vanilla PEFT baselines trained with STABLE match or outperform specialized continual learning methods. In the multimodal setting, STABLE further preserves zero-shot transfer, matching or exceeding dedicated multimodal continual learning methods.

We study the problem of human gaze modeling, which aims to generate the gaze patterns a viewer produces while observing a visual stimulus. Gaze is primarily captured through two modalities: continuous eye-tracking trajectories, which describe fine-grained motion dynamics, and discrete scanpaths, which describe high-level fixation structure. Because gaze varies substantially across viewers and trials, we treat this variability as a defining property rather than noise and model gaze as a stochastic generative process. Existing generative gaze models supervise on only one of these two representations in isolation. We hypothesize that trajectories and scanpaths describe gaze at complementary scales and are jointly informative during training, and test this hypothesis through ST-DiffEye, a joint trajectory-scanpath diffusion framework that couples both modalities by concatenating them as an additional raw input channel, requiring no architectural overhead beyond an input and output channel expansion. We further introduce a principled evaluation framework based on the Continuous Ranked Probability Score (CRPS), which generalizes any existing sequence similarity metric into a proper scoring rule that jointly assesses the accuracy and diversity of generated gaze. Experiments on task-driven visual search, covering both target-present and target-absent scenarios, and on free-viewing benchmarks demonstrate state-of-the-art performance. These results, along with detailed ablations, confirm the benefit of joint modeling and the value of distribution-aware evaluation in capturing the intrinsic variability of human gaze.

3D object grounding localizes referred objects in a 3D scene from natural language. Unified instance-centric 3D-LLMs aim to solve grounding together with dialog, QA, and captioning, yet many rely on a single pointer-style grounding decision that compresses a relational instruction into one selection. This is brittle for fine-grained queries where multiple same-class candidates must be ruled out by context objects and spatial relations. We propose Structured Spatial Reasoning 3D-LLM (SSR3D-LLM), a structured grounding interface for unified 3D-LLMs. Given fixed Mask3D object proposals, the LLM writes a sequence of latent spatial reasoning steps and memory tokens from the query, and a geometry-aware scorer reads these latent steps in order to refine candidate rankings step by step with step-length masking. The latent steps are learned from standard benchmark target supervision with auxiliary referential-cue supervision during training, while inference uses only the input query and Mask3D proposals. Across ReferIt3D, ScanRefer, and Multi3DRef, SSR3D-LLM achieves the strongest results among unified 3D-LLM baselines, with substantial gains over the single-pointer QPG baseline on fine-grained grounding and consistent improvements over prior unified 3D-LLMs, while preserving the default language-task route.

Post-hoc Graph Neural Networks (GNN) explainers typically extract a compact subgraph to preserve the model’s decision rationale. However, this extraction breaks topological integrity and induces a distribution shift, making predictions on subgraphs unreliable and consequently misleading explainer optimization under OOD settings. Existing attempts to build in-distribution proxy graphs often assume independence between explanation and background subgraphs and rely on hard splicing, which causes semantic mismatch and boundary discontinuities that degrade explanation reliability. We propose SSDGExplainer, a Structure–Semantic Dual-Guided explainer that formulates proxy-graph generation as conditional modeling under semantic consistency constraints to achieve deep semantic alignment between the explanation subgraph and the generated background, introduces a topology boundary optimization network to smooth structural fractures at the explanation–background interface, and enforces contrastive semantic constraints to prevent semantic drift. Extensive experiments on synthetic and real-world benchmarks demonstrate consistent improvements over state-of-the-art methods in both explanation quality and fidelity.

We present SS3D, a web-scale SfM-based self-supervision pretraining pipeline for feed-forward 3D estimation from monocular video. Our model jointly predicts depth, ego-motion, and intrinsics in a single forward pass and is trained/evaluated as a coherent end-to-end 3D estimator. To stabilize joint learning, we use an intrinsics-first two-stage schedule and a unified single-checkpoint evaluation protocol. Scaling SfM self-supervision to unconstrained web video is challenging due to weak multi-view observability and strong corpus heterogeneity; we address these with a multi-view signal proxy (MVS) used for filtering and curriculum sampling, and with expert training distilled into a single student. Pretraining on YouTube-8M (~ 100M frames after filtering) yields strong cross-domain zero-shot transfer and improved fine-tuning performance over prior self-supervised baselines. We release the pretrained checkpoint and code.

Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneous robots, sparse workspaces, simplified geometry, offline computation, or handcrafted parameters to make the problem tractable, which limits their deployment in dense crowd scenarios. Toward this end, we propose Shape-Aware Reinforcement Learned Model Predictive Control (SRL-MPC), a method for safe, efficient, and adaptive navigation in crowds with heterogeneous shapes without geometry simplification. To encode shape-aware safety, we formulate high-order control barrier function (HOCBF) constraints from geometric separation features (GSFs) based on support function transformation. A reinforcement learning (RL) framework then learns a neural policy that reads GSFs and outputs real-time MPC parameter updates, enabling the MPC solver to adapt to neighboring crowd geometries. The key advantage of SRL-MPC is that it preserves the safety structure and generalizability of MPC while integrating the adaptability and intelligence of RL. Experiments in randomized crowd scenarios with arbitrary shaped robot fleets demonstrate the effectiveness, scalability, and robustness of SRL-MPC. The results show that SRL-MPC substantially outperforms representative baselines in safety and adaptability.

AI agents are increasingly used to diagnose and mitigate failures of production systems, known as agentic Site Reliability Engineering (SRE). Current SRE benchmarks are limited to oversimplistic SRE tasks and are unfortunately hard to extend due to bespoke designs. We present SREGym, a high-fidelity, interactive benchmark for SRE agents. SREGym exposes a live system environment built atop real-world cloud-native system stacks, where high-fidelity failure scenarios are emulated through fault injectors. SREGym models the complexity of production environments by simulating (1) a wide range of faults across the stack, (2) various ambient noises, and (3) diverse failure modes such as metastable failures and concurrent failures. SREGym is architected as a modular, extensible framework that orchestrates fault injectors and event emulators across stacks; this framework is key to curating high-fidelity, challenging SRE problems. SREGym shows that the effectiveness of frontier models and agents varies significantly (40+%) in mitigating different kinds of problems. SREGym is actively maintained as an open-source project and has been used by many researchers and practitioners.

Modern image super-resolution methods generate detailed, visually appealing results, but they often introduce visual artifacts: unnatural patterns and texture distortions that degrade perceived quality. These defects vary widely in perceptual impact—some are barely noticeable, while others are highly disturbing—yet existing detection methods treat them equally. We propose artifact prominence as an evaluative target, defined as the fraction of viewers who judge a highlighted region to contain a noticeable artifact. We design a crowdsourced annotation protocol and construct SR-Prominence, a dataset suite containing 3,935 artifact masks from DeSRA, Open Images, Urban100, and a realistic no-ground-truth Urban100-HR setting, annotated with prominence. Re-annotating DeSRA reveals that 48.2% of its in-lab binary artifacts are not noticed by a majority of viewers. Across the suite, we audit SR artifact detectors, image-quality metrics, and SR methods. We find that classical full-reference metrics, especially SSIM and DISTS, provide surprisingly strong localized prominence signals, whereas no-reference IQA methods and specialized artifact detectors often fail to generalize across datasets and reference settings. SR-Prominence is released with an objective scoring protocol that allows new metrics to be benchmarked on our suite without further crowdsourcing. Together, the data and protocols enable SR artifact evaluation to move from binary defect presence toward perceptual impact.

Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human annotations are scarce and subjective, reward models are vulnerable to reward hacking, and self-evaluation methods suffer from prompt sensitivity and biases. In this work, we propose **stable rank**, an intrinsic, annotation-free quality signal derived from model representations. Stable rank measures the effective dimensionality of hidden states by computing the ratio of total variance to dominant-direction variance, capturing quality through how information distributes across representation dimensions. Empirically, stable rank achieves 84.04\% accuracy on RewardBench and improves task accuracy by an average of 14.1\% relative to greedy decoding via Best-of-N sampling. Leveraging this insight, we introduce **Stable Rank Group Relative Policy Optimization (SR-GRPO)**, which uses stable rank as a reward signal for reinforcement learning. Without external supervision, SR-GRPO improves Qwen2.5-1.5B-Instruct by 10\% on STEM and 19\% on mathematical reasoning, outperforming both learned reward models and self-evaluation baselines. Our findings demonstrate that quality signals can be extracted from internal model geometry, offering a path toward scalable alignment without external supervision.