NeurIPS 2026 论文列表

Manifold learning is a fundamental task at the core of data analysis and visualisation. It aims to capture the simple underlying structure of complex high-dimensional data by preserving pairwise dissimilarities in low-dimensional embeddings. Traditional methods rely on symmetric Riemannian geometry, thus forcing symmetric dissimilarities and embedding spaces, e.g. Euclidean. However, this discards in practice valuable asymmetric information inherent to the non-uniformity of data samples. We suggest to harness this asymmetry by switching to Finsler geometry, an asymmetric generalisation of Riemannian geometry, and propose a Finsler manifold learning pipeline that constructs asymmetric dissimilarities and embeds in a Finsler space. This greatly broadens the applicability of existing asymmetric embedders beyond traditionally directed data to any data. We also modernise asymmetric embedders by generalising current reference methods to asymmetry, like Finsler t-SNE and Finsler UMAP. On controlled synthetic and large real datasets, we show that our asymmetric pipeline reveals valuable information lost in the traditional pipeline, e.g. density hierarchies, and consistently provides superior quality embeddings than their Euclidean counterparts.

Detecting frequency trend patterns, such as items with sustained growth or decline, is an important and challenging task in high-speed data streams. State-of-the-art solutions require manual tuning of many coupled parameters, while their bloom filters suffer from high false positive rates. In this paper, we propose NeuTrend, a framework that provides accurate and automatic trend detection with high-performance in-network inference. Our key idea is that a lightweight BRNN can learn to classify incoming items as likely trending or non-trending. Thus, it eliminates unqualified items more accurately than a bloom filter and removes the need for manual parameter tuning. The BRNN uses only XNOR and popcount operations. Thus, it aligns with the strict resource constraints of data-plane switches. NeuTrend further introduces an adaptive detection module. The module uses the BRNN confidence scores to automatically tune the growth and decay thresholds. Extensive experiments on real-world datasets show that the learned filter reduces false positive rates by 23\%-44\% and increases effective detector occupancy from 47\% to 70\%. Hence, NeuTrend improves the overall F1 score by 35\%-68\% over existing solutions, and achieves Tbps-level line-rate processing.

Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate should be used under different operating regimes. We present a controlled harness evaluation of memory substrates for memory-augmented agents, covering dense and sparse indices, text records, structural stores, hierarchical stores, refinement-based memories, parametric updates, and activation-compatible context mechanisms. Across three backbone models and four benchmark suites spanning user-centric question answering and agent-centric decision-making, we instrument 26 performance and efficiency metrics under a unified harness. Our results show that no single substrate consistently dominates: broad retrieval benefits long-context factual QA, while excessive retrieval can harm sequential decision-making by shifting attention away from action-critical context. Scalability further introduces an additional routing axis, as substrates that perform well at moderate history lengths can become costly or brittle at longer horizons. These findings motivate substrate routing as a necessary component of adaptive agent memory systems and provide empirical guidance for designing efficient, reliable, and regime-aware long-term memory for LLM agents.

Molecular docking requires reasoning jointly about ligand pose and protein flexibility. Most diffusion-based docking models predict torsional updates with generic Euclidean heads that ignore the periodic geometry of angular variables. This mismatch is especially limiting in flexible docking, where ligand conformations and pocket side chains co-adapt to form the bound complex. Here, we introduce Harmony, a harmonic torsional diffusion framework for flexible protein-ligand docking. Harmony parameterizes ligand and side-chain torsional score fields as derivatives of learned harmonic potentials on the circle, whose noise-level dependence is supplied analytically by the heat semigroup of variance-exploding diffusion on the torus. This construction makes periodicity explicit, removes the need to learn noise conditioning for torsional updates, and gives the model a frequency-aware inductive bias over rotameric motion. On the PDBBind benchmark, Harmony improves ligand pose accuracy and pocket all-atom reconstruction over recent flexible docking methods. On PoseBusters, it improves the physical validity of generated complexes. Case studies on EBNA1 and KRAS G12D illustrate the method's behavior on a polar and a shallow binding site, respectively. Together, these results indicate that aligning the score parameterization with the geometry of the diffusion process is a simple and effective lever for improving flexible docking.

In this work, we investigate how the internal representations of Large Language Models (LLMs) change with inputs of increasing difficulty. Although sparsity changes may not be obvious for individual samples, dataset-level results reveal a consistent statistical trend: as task difficulty increases (e.g., harder questions, longer contexts, or more answer choices), the last hidden states of LLMs become systematically sparser. In short, \emph{the harder the task, the sparser the representation}. This sparsity--difficulty relation is observable across diverse models and domains, suggesting that harder inputs drive more concentrated activation patterns in the last hidden state. Through a series of controlled analyses and learning-dynamics experiments, we show that representational density is a learned property of data familiarity: models develop rich, distributed representations for mastered patterns, while unfamiliar inputs default to sparser activations. Our finding is also actionable. We illustrate this with Sparsity-Guided Curriculum In-Context Learning (SG-ICL), which uses sparsity to select few-shot demonstrations matched to the query's difficulty, outperforming standard CoT and Auto-CoT baselines on MATH-500. Our study provides new insights into how LLM representations reflect task difficulty and how this signal can be leveraged for inference.

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of frontier models across 54 benchmarks, enabling a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Mix, a curated set of 100 difficult, diverse, and high-quality tasks refined from the adapted benchmarks. Harbor-Mix preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; the strongest model resolves only 15.6\% of its tasks. We release the adapters, evaluation results, in-depth analysis, and Harbor-Mix as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

In self-supervised pretraining for Handwritten Text Recognition (HTR), pixel reconstruction methods tend to outperform contrastive ones, a pattern that sits awkwardly with recent evidence that pixel reconstruction yields uninformative features for natural-image classification. We argue this discrepancy is not an accident, but a consequence of how HTR signal is distributed in pixel space. By probing the input distribution directly, we show that HTR's discriminative content is concentrated in the high-variance pixel subspace and is essentially absent from the low-variance one, the inverse of the structure observed for image classification. Under this view, the right SSL family becomes predictable: objectives that preserve high-variance pixel content should transfer best. We test this prediction across six SSL methods spanning three families (pixel-grounded MIM, JEPA-style, contrastive image--image and image--text), under matched encoder, data, and evaluation protocols on six handwriting benchmarks across five languages. Pixel-grounded SSL produces the lowest CER on every benchmark and every probe, exposes per-position character information that other families recover only via the readout, and is the only family that benefits from real-data pretraining. A geometric property of the encoder, its alignment with the high-variance pixel subspace, predicts CER within every SSL method we test. With a pretrained LLM decoder, a frozen pixel-grounded encoder is already competitive with fully fine-tuned supervised baselines, and full fine-tuning beats them on the mean and ranks first or second on every benchmark. These results challenge the prevailing view that pixel reconstruction wastes capacity on irrelevant detail: whether reconstruction is wasted depends on where the discriminative signal lives in the input.

Hand radiographs support diverse clinical tasks, including skeletal maturity assessment, rheumatoid arthritis scoring, abnormality screening, and anatomical localization, yet existing models are typically trained separately for each task and dataset. We present HandXFM, a domain-specific foundation model that leverages cross-modality knowledge for comprehensive hand X-ray understanding. HandXFM distills semantic priors from BiomedCLIP and structural cues from a chest X-ray Vision Transformer (ViT) through a unified alignment framework, integrating complementary medical knowledge in an interpretable way. After pretraining, HandXFM can be adapted to a range of musculoskeletal tasks, including bone age estimation, SvH score prediction, abnormality detection, joint localization, bone segmentation, and visual question answering. It consistently outperforms task-specific and single-expert baselines, achieving up to 0.11 improvement in Pearson correlation coefficient (PCC) for bone age prediction and a 12\% accuracy gain in abnormality classification. Moreover, HandXFM generalizes to unseen datasets and yields cross-attention maps linking clinical terms to anatomical regions. These results demonstrate that multi-expert distillation effectively unifies semantic and structural supervision within a single pretrained model, establishing HandXFM as an interpretable and generalizable foundation model for hand radiograph analysis.

Robotic manipulation with dexterous hands is a cornerstone of Embodied AI, yet its progress is stifled by the high cost of collecting embodiment-aware teleoperation data. While abundant egocentric videos of human hands offer a scalable alternative, the profound discrepancies in appearance, articulation, and camera viewpoints between human and robotic data raise significant challenges for co-training. Though existing general image-editing models demonstrate strong capabilities, they lack necessary embodiment-specific priors to fully bridge this gap. In this work, we present HandEdit, a unified large-scale embodiment-aware image-editing dataset and benchmark specifically designed to transform human hands and arms into various dexterous robotic embodiments within egocentric frames. HandEdit comprises over 200M editing instances derived from five diverse source datasets, covering 26 distinct URDFs, including 13 hand-only and 13 hand-arm configurations. Alongside the dataset, we establish a unified benchmark protocol with two tracks: Hand-only and Hand-Arm, supporting URDF-conditioned evaluation. We conduct extensive evaluations of 11 representative image-editing baselines using a multi-dimensional metric suite, including generic similarity metrics, VLM-based judgment, and embodied-aware metrics. HandEdit serves as a critical resource at the intersection of image editing and robotics: it advances embodiment-aware editing models while enabling scalable dexterous robotic learning from abundant human video data, paving the way for more generalizable Embodied AI. Code, datasets, and benchmarks are available at \url{https://anonymous.4open.science/r/HandEdit}.

Selective unlearning in large language models is increasingly necessary for safety and compliance, yet harmful or memorized content is often latent, entangled, and hard to specify as a clean ``forget set.'' We aim to close this gap by identifying what to forget from the model’s own failure modes rather than relying solely on explicit supervision. We propose Hallucination-Guided Unlearning (HGU), which treats hallucinations as diagnostic signals: it localizes unsupported spans via evidence and internal consensus, traces a sparse set of high-responsibility MLP neurons, and edits them with compact gates under a utility-preserving KL constraint. Across TOFU, HGU achieves the best MU--FE trade-off with Avg of 0.7221 (forget05) and 0.7699 (forget10), and it also attains the top SepS H-Avg (0.4382/0.4715) under mixed forget/retain prompts; on WMDP auxiliary, it yields the strongest forgetting (e.g., 14.2 on Economics) while improving Retain (52.7) and MMLU (57.2). These results suggest that reframing hallucinations as actionable traces enables targeted, post-hoc unlearning that better balances forgetting efficacy and general utility without full retraining.

Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and correctly when it is present. We test this assumption by introducing a semantic notion of answer availability that aggregates token-level variants expressing the same answer concept, and asks whether the correct concept is already available at the moment the model commits to an answer. Across Qwen and Llama models from 0.8B to 72B in both Instruct and Base variants, 16-47\% of Instruct hallucinations occur with substantial probability mass already on the correct concept, and the rate rises monotonically with scale. Comparing such failures against correct generations with matched semantic support, the distinguishing factor is not whether the correct concept is represented, but how its probability is distributed: correct generations concentrate mass on a single surface form, hallucinations disperse it across alternatives. The same sharpening asymmetry extends across multi-token generation and is detectable in pre-generation hidden states. Together, these results identify a single mechanism: instruction tuning sharpens answer commitment with scale, making helpfulness and confident hallucination two consequences of the same underlying disposition.

Diffusion-based image restoration models produce visually compelling results but systematically hallucinate text---generating characters that appear sharp and legible yet are factually incorrect. As text fidelity emerges as a key requirement for real-world image restoration, this failure mode poses a fundamental barrier to wide deployments of diffusion-based models: a model that replaces degraded-but-faithful text with sharp-but-wrong text misleads users and erodes trust. Recent text-aware models mitigate this by feeding text extracted from intermediate outputs or low-resolution (LR) images into the prompt, but they provide no mechanism to detect or correct the hallucinations that still commonly arise. In this work, we present a systematic study on how to improve text restoration during denoising, demonstrating that standard global conditioning alone is inadequate and that optical character recognition (OCR) confidence scores reliably predict word-level correctness. Grounded in these findings, we propose HalluciText, a training-free framework consisting of two complementary interventions: (i) Confidence-Weighted Classifier-Free Guidance (CW-CFG), which concentrates guidance energy on text regions weighted by OCR confidence to improve text recall; and (ii) VLM-Guided Test-Time Guidance (V-TTG), which leverages a vision-language model (VLM) to identify hallucinated regions and corrects them towards a faithful reference, improving text precision. Both operate solely on the noise prediction or latent representation, making them agnostic to the diffusion backbone and text spotting model. We demonstrate the effectiveness of HalluciText on state-of-the-art (SOTA) text-aware models, achieving up to 5.75 points of improvement in end-to-end text recognition F1 on several datasets without degrading image quality.

Hallucination remains a central failure mode of large language models, but existing benchmarks operationalize it inconsistently across tasks such as summarization, question answering, retrieval-augmented generation, and agentic interaction. This fragmentation makes it unclear whether a mitigation that works in one setting actually reduces hallucinations across contexts. Current hallucination benchmarks either require human annotation and fixed references that may eventually be memorized, or rely on naturalistic observations which are often recorded in settings that are difficult to reproduce or test systematically. To enable further research on the root causes of hallucination, we introduce HalluWorld, an extensible benchmark framework grounded in an explicit reference-world formulation: a model hallucinates when it produces an observable claim that is false with respect to this reference world. Building on this view, we construct a family of synthetic and semi-synthetic benchmark environments in which the reference world is fully specified, the model's observable view is controlled, and hallucination labels can be generated automatically by construction. HalluWorld spans multiple settings that are classically representative for AI, i.e., gridworlds, chess, and realistic terminal tasks. This enables controlled variation of key factors such as world complexity, observability, temporal change, and source-conflict policy, allowing us to disentangle hallucinations into more fine-grained error categories. We evaluate frontier and open-weight language models across these settings and find consistent patterns across domains: perceptual hallucination on directly observed information is near-solved for frontier models, while multi-step state tracking and causal forward simulation are still difficult for frontier models, and are not generally solved by extended thinking. In the terminal setting specifically, models also struggle with when to abstain from answering. The uneven profile of failures across probe types and domains suggest that different hallucinations arise from qualitatively distinct failure modes rather than reflecting a single underlying capability. Our results suggest that controlled reference worlds offer a scalable and reproducible path toward measuring and reducing hallucinations in modern language models.

When a text description is extended with an additional detail, image-text similarity should drop if that detail is wrong. We show that CLIP-style dual encoders often violate this intuition: appending a plausible but incorrect object or relation to an otherwise correct description can increase the similarity score. We call such cases \emph{half-truths}. On the verified COCO evaluation set, CLIP prefers the correct shorter description only 41.0\% of the time, and performance drops to 28.2\% when the added detail is a relation. We trace this vulnerability to weak supervision on caption parts: contrastive training aligns full sentences but does not explicitly enforce that individual entities and relations are grounded. We propose CS-CLIP (Component-Supervised CLIP), which decomposes captions into entity and relation units, constructs a minimally edited foil for each unit, and fine-tunes the model to score the correct unit above its foil while preserving standard dual-encoder inference. CS-CLIP raises half-truth accuracy to 78.2\% and improves average performance on established compositional benchmarks by 5.7 points, suggesting that reducing half-truth errors aligns with broader gains in compositional understanding.

Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity from the network, and effective rank collapses, leaving surviving neurons redundant. Existing remedies such as periodic resets, and special neural network architectures, are largely algorithm- or domain-specific. We propose a simple architectural fix, the Hadamard Representation (HR), which replaces a standard hidden layer with the element-wise product of two independently parameterized layers. HR operates through two complementary mechanisms. First, it reduces the probability of a neuron becoming dormant, which is particularly valuable for continuously differentiable activations such as $\tanh$: unlike dormant ReLU neurons, which are effectively pruned, saturated $\tanh$ neurons silently corrupt downstream layers by turning their outgoing weights into fixed biases. Second, independently of dormancy, the multiplicative structure captures richer feature interactions and increases effective rank without widening the layer. We evaluate HR across five algorithms and three domains: DQN, PPO, and PQN on pixel-based discrete-action Atari, SimbaV2 on state-based continuous control, and MR.Q on visual continuous control. HR consistently improves performance over the strong baselines without any hyperparameter tuning, and gains persist against parameter-matched wider variants, ruling out parameter count as an alternative explanation.

Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended objective. Reward hacking has been observed across a wide range of settings, yet methods for reliably measuring it at scale remain lacking. In this work, we introduce a new evaluation paradigm for measuring reward hacking. Whereas prior studies have primarily analyzed it post hoc by inspecting agent trajectories, we instead embed detectable reward hacking opportunities directly into environments. This makes their exploitation verifiable by design, enabling deterministic and automated measurement of whether and how agents exploit such vulnerabilities. We instantiate this approach in TextArena and release Hack-Verifiable TextArena, a testbed in which reward hacking can be measured reliably. Using this benchmark, we analyze reward hacking behavior across language models in diverse environments and settings.

We propose, HaNDF, object-conditional neural distance fields as data-driven priors for modeling the plausible hand–object configurations, in the product manifold of hand articulations. While recent unconditional generative priors showed success in modeling human pose, hands are versatile articulated bodies often found in interaction with other objects. This makes it crucial to develop a generative prior which can model the plausible hand poses conditioned on the object under interaction. To this end, our HaNDF proposes a geometry-aware, object-conditioned neural distance field, representing the plausible articulations in the zero-level set of a conditional field. We leverage tools from Riemannian geometry to (i) represent plausible hands in the zero level-set of an object-induced neural field, and (ii) project a given pose onto the this field. Using HaNDF, we can also optimize for a plausible condition, determining the object under interaction. Our extensive evaluations demonstrate that our HaNDF provides a flexible and powerful prior for hand–object interaction, suitable for applications such as pose refinement, reconstruction under occlusion, and physically plausible manipulation synthesis.

World models enable model-based planning through learned latent dynamics, but imagined rollouts often become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability arises from two missing structures in planner-facing latents: history-conditioned memory for approximate Markov completeness, and geometric organization that separates configuration, momentum, and task semantics. We propose HaM-World, a structured world model that decomposes the latent state into a canonical $(q, p)$ subspace and a context subspace $c$, while incorporating Mamba selective state-space memory as a history-conditioned input to the same latent dynamics. Within this unified interface, $(q, p)$ evolves under a Soft-Hamiltonian dynamics composed of an energy-derived Hamiltonian vector field and learnable residual and control dynamics, while $c$ captures semantic, dissipative, and non-conservative factors. This design provides the planner with a single latent representation shared across dynamics prediction, reward and value estimation, imagined rollouts, and cross-entropy method (CEM) planning. On four DeepMind Control Suite tasks, HaM-World achieves the highest average AUC (+9.5% over strong baselines), reduces long-horizon rollout error to 45% of a competitive model, and wins 11 out of 12 $k \in \{3,5,7\}$ rollout MSE metrics. Under 12 out-of-distribution perturbations, HaM-World consistently attains the highest returns, with average gains of 10.2% on Finger Spin and 13.6% on Reacher Easy. Mechanism diagnostics further demonstrate bounded energy drift under action-free rollouts, structured energy variation under policy control, and coherent control-induced energy transfer, supporting the effectiveness of the proposed Soft-Hamiltonian latent dynamics. Code: https://anonymous.4open.science/r/HaM_World-47CD

Large language models (LLMs) are increasingly adopted for software and hardware design, yet these domains are still evaluated separately. Software benchmarks typically assume fixed hardware targets, while hardware benchmarks focus on component-level optimization without considering the full hardware-software stack. Consequently, no existing benchmark evaluates whether an LLM agent can perform end-to-end, system-level hardware-software co-design. Such a process requires: 1) analyzing applications to identify kernels requiring acceleration, 2) designing and \emph{integrating} heterogeneous accelerators into a System-on-Chip (SoC) under resource constraints, and 3) mapping kernels onto the generated accelerators. We present \hsco{}, an end-to-end hardware-software co-design benchmark for accelerator-rich heterogeneous SoC generation. Built upon an open-source SoC platform with a curated repository structure, HSCO-Bench evaluates the ability of LLMs to jointly optimize software and hardware stacks, producing SoC prototypes deployed on the AMD Virtex-7 FPGA VC707 Evaluation Kit. Experimental results show that end-to-end integration remains challenging for current models, with widespread failures. Among the five frontier models evaluated, only two of them could successfully generate valid SoC prototypes. Yet, even in these successful instances, the generated designs are far from optimal. While we observe a promising peak speedup of 16.22x, the maximum additional resource utilization reaches only 23.67%. This highlights that while state-of-the-art models demonstrate an emerging capability for hardware acceleration, they still heavily underutilize the available hardware capacity, leaving substantial room for future optimization. To the best of our knowledge, HSCO-Bench is the first benchmark targeting this complete co-design flow, enabling LLMs to jointly reason about and modify both the software and hardware stacks of heterogeneous SoCs.