NeurIPS 2026 论文列表

While LLM-based coding agents have advanced to repository-scale engineering, existing benchmarks predominantly focus on software maintenance, overlooking the foundational capability of system construction. We introduce CSBench, a benchmark evaluating project-level Spec-to-Code implementation across core computer science domains (e.g., OS, compilers, databases). CSBench features 100 expert-curated tasks from top-tier university assignments within containerized environments. Evaluating 12 state-of-the-art LLMs reveals a stark performance disparity: even top-tier models like GPT-5.2 see success rates plummet from over 90% in algorithmic tasks to below 35% in system-level domains. Our analysis identifies a fundamental deficiency in systemic reasoning and construction knowledge as the primary bottleneck, where agents either terminate prematurely due to overconfidence or fail to translate execution feedback into valid architectural fixes, highlighting CSBench as a necessary tool to bridge this gap and advance autonomous agents toward deep computer science mastery.

Code-switching (CS), the alternation between two or more languages within a single conversation, presents significant challenges for automatic speech recognition (ASR) systems. Existing Mandarin-English code-switching datasets often suffer from limitations in size, spontaneity, and the lack of full-length dialogue recordings with transcriptions, hindering the development of robust ASR models for real-world conversational scenarios. This paper introduces CS-Dialogue, a novel large-scale Mandarin-English code-switching speech dataset comprising 104 hours of spontaneous conversations from 200 speakers. Unlike previous datasets, CS-Dialogue provides full-length dialogue recordings with complete transcriptions, capturing naturalistic code-switching patterns in continuous speech. We describe the data collection and annotation processes, present detailed statistics of the dataset, and establish benchmark ASR performance using state-of-the-art models. Our experiments, using Transformer, Conformer, and Branchformer, demonstrate the challenges of code-switching ASR, and show that existing pre-trained models such as Whisper still have the space to improve. The CS-Dialogue dataset will be made freely available for all academic purposes.

Offline RL methods often regularize toward the empirical occupancy of the dataset, but this reference can mismatch the deployed policy. In partially observed or decentralized settings, data may be pooled from hidden modes, histories, or conventions that are unavailable at execution time. The pooled occupancy can then require incompatible action laws for the same deployed input, or joint correlations that a decentralized policy class cannot represent, so regularization toward it can favor a low return projection. We formalize this failure through *reference coherence*: a reference is coherent when it does not rely on information hidden from the deployed policy, and when its action law is representable by that policy. We propose *Closest Slice DICE (CS-DICE)*, a DICE variant that regularizes toward a coherent slice of the training data rather than the pooled occupancy. A hard or soft selector chooses the slice used as the reference term, while the deployed observations, actor class, and factorization constraints remain unchanged. Most of the results focus on the soft reverse-$KL$ case, where the selector only changes the reference used by an otherwise standard DICE update. Controlled examples show that incoherent pooled references collapse to suboptimal behavior, while CS-DICE recovers high return policies when the selected or inferred slice is coherent with the deployed interface. We also identify a boundary case where pooling is benign because the relevant signal is revealed before the conflict. Finally, a CS-CoMA-DICE study on MaMuJoCo shows that selected references can be integrated into a neural cooperative MARL pipeline while preserving decentralized execution.

Prior-fitted networks (PFNs) are a promising class of tabular foundation models that perform in-context learning, whereby the entire labelled training set is supplied as context, and predictions for test queries are produced in a single forward pass. However, the quadratically scaling self-attention mechanism in many PFN architectures makes inference prohibitive for very large training datasets. We propose CRUMB (Clustered Retrieval Using Minimised-MMD Batching), a three-stage inference wrapper that (i) clusters the test queries, (ii) selects a small, distributionally matched training subset for each cluster by greedily minimising the maximum mean discrepancy (MMD), and (iii) runs exact PFN inference on each reduced-context batch. CRUMB is architecture-agnostic and requires no retraining. On the 51-dataset TabArena benchmark, evaluated across three PFN architectures (TabPFNv2, TabICLv1, TabICLv2), we show that CRUMB outperforms similar state-of-the-art context selection strategies. We also show that CRUMB is resilient to covariate drift, as the MMD-minimisation step naturally helps align the training context distribution to match the current test batch distributions.

Latent LiDAR pipelines suffer from flying pixels: convolutional VAEs blur sharp LiDAR contours, yielding edge depths that back-project to points floating between surfaces. We identify this as a major, directly correctable decoder bottleneck and introduce CRISP: a pixel-space diffusion decoder with a backbone-agnostic latent adapter, DiT-based denoiser, and support mask predictor. CRISP replaces convolutional decoders commonly inherited from image and video VAEs while keeping the encoder and latent generator fixed. Across KITTI-360, SemanticKITTI, and nuScenes, replacing only the decoder reduces FSVD/FPVD by 50.5% on average across frozen backbones; for generic video VAEs, the reductions reach 71%/74%. On the LiDAR-native LiDM backbone, FRID drops by 71%, with the largest gains at depth discontinuities. Inside a pretrained LiDM world model, the same zero-shot replacement improves FSVD by 15.5%, narrowing the sim-to-real gap. Code and checkpoints will be released upon acceptance.

Simultaneous Speech Translation (SimulST) requires balancing translation quality and latency. While Large Language Models (LLMs) excel in offline translation, current LLM-based SimulST systems predominantly rely on prefix-incremental generation. This paradigm suffers from redundant Key-Value cache recomputation and necessitates external Voice Activity Detection to process unbounded streams. To overcome these bottlenecks, we propose an end-to-end interleaved read-write framework built upon an omni-modal LLM. By interleaving speech chunks and text tokens, our architecture achieves full KV cache reuse, natively supporting segmentation-free, infinite-length inference. Furthermore, to learn optimal streaming policies without rigid offline alignments, we introduce a novel Actor-Critic self-enhancement pipeline. An RNN-T Actor dynamically samples read-write trajectories, while an LLM-based Critic evaluates these paths via intrinsic semantic and latency rewards, distilling the optimal policy back to the Actor. Extensive experiments on sentence-level (FLEURS, CoVoST2) and document-level (MuST-C, ACL 60/60) benchmarks demonstrate that our model establishes new state-of-the-art quality-latency Pareto frontiers, substantially outperforming existing cascaded and static-alignment baselines.

Traditional forecasting evaluations relying on static historical data are fundamentally incompatible with modern AI advances. Even for standard time series foundation models, temporal overlap between training and test periods can lead to implicit leakage through correlated signals. This problem is intensified by LLMs, which can bridge semantic gaps between forecasted and related data while memorizing extensive world knowledge. At the extreme, agentic models with tool access can retrieve the ground truth directly. Such information leakage inflates performance relative to real forecasting scenarios and is impossible to rule out in historical evaluations. We introduce CREF, a real-time benchmark that evaluates forecasting models on data that does not yet exist, eliminating all forms of leakage by design. CREF balances three competing objectives for real-time benchmarks: diversity, robustness, and throughput. It draws data from 32 public APIs and features 50 forecasting tasks with diverse data frequencies, multivariate targets, and covariates, making it the first real-time benchmark reaching the breadth of leading static benchmarks. Retrospective evaluation validates that CREF produces rankings consistent with established static benchmarks, while real-time evaluation reveals qualitative and quantitative performance gaps for agentic and LLM-based models, confirming leakage on historical data. CREF runs continuously and is open for new models to join, offering a public leaderboard for contamination-free model comparison.

Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary but misaligned. The Instruct model is concise and tool-disciplined, whereas the Thinking model offers stronger planning and recovery behavior but often over-deliberates and degrades agent performance. We present CRANE (Constrained Reasoning Injection for Code Agents via Nullspace Editing), a training-free parameter-editing method that treats the Thinking–Instruct delta as a directional pool of candidate reasoning edits for the Instruct backbone. CRANE combines magnitude thresholding to denoise the delta, a Conservative Taylor Gate to retain edits that are jointly beneficial for reasoning transfer and tool-use preservation, and Graduated Sigmoidal Projection to suppress format-critical update directions. By merging paired Instruct and Thinking checkpoints, CRANE delivers strong gains over either individual model while preserving Instruct-level efficiency: on Roo-Eval it achieves pass@1 of 66.2% (+19.5%) for Qwen3-30B-A3B and 81.5% (+8.7%) for Qwen3-Next-80B-A3B; on SWE-bench-Verified it resolves up to 14 additional instances at both scales (122/500 and 180/500); and on Terminal-Bench v2 it improves pass@1/pass@5 by up to 2.3%/7.8%, reaching 7.6%/17.9% and 14.8%/30.3%, respectively, consistently outperforming alternative merging strategies across all three benchmarks.

Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit fundamental trade-offs: closed-loop RL fine-tuning provides grounded feedback from executed actions but is constrained by the sparsity of informative events, whereas counterfactual fine-tuning provides dense supervision over candidate futures but inherits bias from imperfect future estimates. We introduce Counterfactual-to-Interactive Reinforcement Fine-Tuning (CRAFT), an on-policy framework that formulates closed-loop post-training as proxy-residual optimization. CRAFT uses group-normalized counterfactual advantages as a dense proxy for real closed-loop advantages and aligns this proxy with the closed-loop world through grounded residual correction from interaction-critical events. To stabilize adaptation, CRAFT regularizes the online policy toward an EMA teacher via asymmetric KL self-distillation. Theoretically, CRAFT decomposes the real closed-loop policy gradient into proxy and residual terms under the same visited-state distribution, reducing residual variance with an aligned proxy while mitigating proxy bias through grounded residual approximation. Empirically, CRAFT achieves the strongest closed-loop gains on Bench2Drive across hierarchical planning, vision-language-action, and vocabulary-scoring architectures. Ablations, scaling behavior, stability analyses, and transfer results further validate the complementary roles of dense counterfactual proxy and grounded residual correction.

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) over heterogeneous data distributions. Naive averaging, as used in FedAvg, often leads to destructive interference in which the global model improves on average but deteriorates significantly for specific clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a \emph{reference direction} while satisfying \emph{conflict-free constraints}, ensuring non-negative alignment with the updates of participating clients. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates destructive interference through its projection geometry. Extensive experiments on non-IID and imbalanced benchmarks demonstrate that CRAFT significantly reduces performance disparity while maintaining competitive global accuracy against state-of-the-art baselines.

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout cost, making low-precision rollout appealing for acceleration. However, applying low-precision formats such as FP4 to RL remains unstable, even with quantization-aware training (QAT) enhancements. We identify that the root cause is that FP4’s aggressive quantization amplifies small system-level numerical differences (i.e., training-inference stack mismatch) that are harmless at BF16 into large token-level log-probability errors, distorting importance weights and destabilizing optimization. To address this, we propose Cross-Precision Alignment (CPA), a simple regularizer that stabilizes low-precision RL by maintaining a BF16 master policy, executing rollouts in real FP4, and aligning the fake-quantized forward pass with a BF16 reference forward pass on sampled tokens by applying a low-variance KL penalty at each training step. In our evaluation, the resulting BF16 checkpoint matches a full BF16 RL baseline, and the overall pipeline delivers 8–19\% end-to-end training speedup.

Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.

In cooperative teams where agents act in a fixed order and share a single team-level reward (multi-agent language systems, sequential robotic tasks), per-agent credit assignment is under-determined. Critic-based approaches scale poorly as the number of agents grows owing to the costly maintenance of joint/factored critic(s), whereas the existing critic-free alternatives have other issues: common credit across agents that couples every agent's signal to teammate noise, importance-sampling corrections for upstream-update staleness that incur variance exponential in team size, or per-agent counterfactual replay that isolates each agent's effect at the price of extra environment or reward calls. We propose COSAC, a critic-free per-agent policy gradient for sequential cooperative teams. COSAC fits an additive per-agent decomposition of the team reward by a single ridge regression on the rollout batch (giving each agent a learning signal decoupled from teammate noise), and computes each agent's counterfactual advantage from fictitious continuations of the current policy (policy forward passes that replace both importance-sampling reweighting and per-agent environment replay, at no extra environment or reward cost). The estimator instantiates the **Sequential Aristocrat Utility** (SeqAU), our extension of Wolpert and Tumer's (2001) aristocrat utility to sequential teams. We prove bias and variance bounds on SeqAU credits that stay controlled as the team grows. Our controlled study on sequential bandits demonstrates that COSAC attains the lowest advantage MSE and consistently low learning regret across team sizes up to $K = 16$. On the AI2 Reasoning Challenge (ARC) task, where four Qwen3-0.6B agents reason in turn about a grade-school science question, COSAC attains faster convergence than the other critic-free baselines.

Intracranial electrocorticography (ECoG) offers high–signal-to-noise access to cortical activity for brain–computer interfaces, yet limited per-patient data has led most prior work to rely on small, subject-specific decoders that neglect information shared across patients. We investigate whether large pretrained scalp-EEG foundation models (EEG FMs) can be adapted to ECoG, enabling cross-patient learning and competitive decoding performance while calibrating to a held-out patient in $10$--$30$ minutes on a single GPU. We introduce CORTEG, a cross-modality transfer framework that combines a pretrained EEG FM backbone, an electrode-aware KNNSoftFourier spatial adapter, a dual-stream tokenizer for low-frequency and high-gamma activity, and a leave-one-subject-out fine-tuning strategy. We evaluate CORTEG on two challenging regression tasks: public finger trajectory regression (n=9) and private audio envelope regression (n=16). CORTEG matches or exceeds the strongest task-specific baselines on both tasks: it reaches the highest mean correlation among compared methods on the public finger benchmark (gain not statistically significant on $n{=}9$ subjects), with larger and statistically significant gains on the audio task and in low-data per-patient calibration. Feature analyses align with neurophysiology, and latent manifolds capture low-dimensional finger-movement structure. CORTEG provides systematic evidence that scalp-EEG pretraining can be repurposed for ECoG decoding, enabling data-efficient intracranial BCIs that can adapt to new patients.

Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely on retraining or multi-stage optimization, which limits post-training deployment. We propose CORP, a closed-form one-shot structured pruning method that removes MLP dimensions and attention substructures using only unlabeled calibration data without labels, gradients, or fine-tuning. CORP formulates structured pruning as a representation recovery problem. It models removed components as affine functions of retained components and derives closed-form ridge regression solutions that fold compensation into model weights. This minimizes the expected representation error under the calibration distribution. Experiments on ImageNet with DeiT reveal strong redundancy in both MLP and attention representations. Without compensation, one-shot structured pruning causes severe accuracy loss. With CORP, models retain high accuracy under aggressive sparsity. On DeiT-Huge, CORP achieves 83.27% Top-1 accuracy after pruning 50% of both MLP and attention structures.

Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved encouraging results on local image blocks, it remains unclear whether such progress translates to reconstruction that is both structurally accurate and scalable to the whole-brain scale. We present CORAL, the first benchmark for structure-aware evaluation of automatic neuron reconstruction from light microscopy images at both local and whole-brain scales. Built on a high-quality whole-brain fMOST dataset with carefully curated annotations, CORAL establishes two progressive tasks: block-level reconstruction, which evaluates reconstruction methods under limited spatial context, and brain-wide reconstruction, which assesses complete neuron reconstruction at the whole-brain scale. To account for topological correctness beyond geometric distance similarity, we introduce a structure-aware metric based on fiber prediction. To further achieve complete neuron reconstruction across the entire brain, we develop a brain-wide neuron tracing framework that extends arbitrary local reconstruction methods to the whole-brain scale through an iterative local-to-global process. Using this benchmark, we provide the first structure-aware comparison of mainstream methods for local neuron reconstruction and further evaluate their performance in brain-wide reconstruction. Our results underscore the importance of structure-aware evaluation and the need for more robust methods for complete neuron reconstruction. All datasets and code are available at https://github.com/yang-ze-kang/CORAL.

Parameter-Efficient Fine-Tuning (PEFT) commonly adapts pretrained weights through low-rank updates, and recent methods further exploit the singular value decomposition (SVD) of the base weight for initialization or subspace selection. However, these methods do not explicitly preserve the coupled geometry between the pretrained left and right singular bases. Motivated by recent minimum-perturbation theory, which shows that stable finetuning admits a coherent SVD rotation in which a single orthogonal $Q$ acts on both the left singular basis $U_0$ and the right singular basis $V_0$, we prove a per-slice analogue: each row slice of $W_0$ can be adapted by a shared orthogonal rotation $Q_i$ on its left basis $U_i$ and right basis $V_i$ together with a diagonal spectrum shift. We instantiate this form as **CORA** (*Coherent Orthogonal Rotation Adaptation*), which applies per-slice orthogonal rotations and a per-layer diagonal scale to the rank-$r$ SVD truncation of $W_0$. CORA uses $\tfrac{1}{2}m(r{-}1)$ trainable parameters per linear layer, about $4{\times}$ fewer than LoRA at the same rank. CORA outperforms LoRA, DoRA, PiSSA, and MiLoRA on commonsense reasoning and code generation while using $\sim 8{\times}$ fewer parameters.

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD) strategies leading to low-rank approximations of the original model weights. However, the underlying single shared subspace modeling can degrade accuracy even at moderate compression. Sparse dictionary learning provides a more flexible union-of-subspaces representation, but existing approaches often suffer from costly iterative dictionary and coefficient updates. We propose **COMPOT** (**C**alibration-**O**ptimized **M**atrix **P**rocrustes **O**rthogonalization for **T**ransformers), a training-free compression framework that uses a small calibration dataset to estimate a sparse weight factorization. COMPOT employs orthogonal dictionaries that enable closed-form Procrustes updates for the dictionary and analytical single-step sparse coding for the coefficients, reducing significantly the overall optimization cost. To handle heterogeneous layer sensitivity under a global compression budget, COMPOT further introduces a one-shot dynamic allocation strategy that adaptively redistributes layer-wise compression rates. Extensive experiments across diverse architectures and tasks show that COMPOT consistently delivers a superior quality–compression trade-off over strong low-rank and sparse baselines, while remaining fully compatible with post-training quantization for extreme compression. Code will be released upon acceptance.

3D human pose estimation from sparse multi-view camera rigs is an essential task for numerous applications, including action recognition, sports analysis, and human-robot interaction. While learned methods dominate the field on benchmarks, they require large annotated datasets; training-free optimization-based methods remain promising as they circumvent 3D supervision by solving a correspondence problem across views from 2D detections. Existing combinatorial formulations rely on pairwise associations to model this correspondence problem and enforce global consistency across views only as a downstream constraint. However, reconciling locally plausible pairwise matches becomes brittle under occlusion and noisy detections, where local errors propagate globally. We propose COMPOSE, which recasts multi-view 3D human pose estimation as a weighted exact-cover optimization over a hypergraph of person hypotheses. Our formulation replaces pairwise association and post-hoc consistency enforcement with a single global combinatorial objective. To address the exponentially large candidate space, we introduce a geometric pruning strategy alongside two complementary solvers: an exact Integer Linear Programming formulation and a scalable relaxation via Belief Propagation. Without any 3D supervision, COMPOSE improves average precision by up to 31 points over the best optimization-based method and 13 points over self-supervised learned methods, demonstrating the effectiveness of higher-order combinatorial association for training-free multi-view 3D human pose estimation.