NeurIPS 2026 Papers

Video-based world models hold significant potential for generating high-quality embodied manipulation data. However, current video generation methods struggle to achieve stable long-horizon generation: classical diffusion-based approaches often suffer from temporal inconsistency and visual drift over multiple rollouts, while autoregressive methods tend to compromise on visual detail. To solve this, we introduce LongScape, a hybrid framework that adaptively combines intra-chunk diffusion denoising with inter-chunk autoregressive causal generation. Our core innovation is an action-guided, variable-length chunking mechanism that partitions video based on the semantic context of robotic actions. This ensures each chunk represents a complete, coherent action, enabling the model to flexibly generate diverse dynamics. We further introduce a Context-aware Mixture-of-Experts (CMoE) framework that adaptively activates specialized experts for each chunk during generation, guaranteeing high visual quality and seamless chunk transitions. Extensive experimental results demonstrate that our method achieves stable and consistent long-horizon generation over extended rollouts. Our code is available at: https://anonymous.4open.science/r/AMSVVD-fdg245.

Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition dynamics. Existing methods typically address dynamics mismatch either globally over the state space or via pointwise data filtering; these approaches can miss localized cross-domain similarities or incur high computational cost. We propose Localized Dynamics-Aware Domain Adaptation (LoDADA), which exploits localized dynamics mismatch to better reuse source data. LoDADA clusters transitions from source and target datasets and estimates cluster-level dynamics discrepancy via domain discrimination. Source transitions from clusters with small discrepancy are retained, while those from clusters with large discrepancy are filtered out. This yields a fine-grained and scalable data selection strategy that avoids overly coarse global assumptions and expensive per-sample filtering. We provide theoretical insights and extensive experiments across environments with diverse global and local dynamics shifts. Results show that LoDADA consistently outperforms state-of-the-art off-dynamics offline RL methods by better leveraging localized distribution mismatch.

Evidence-grounded medical question answering requires not only accurate answers, but also precise, verifiable, and clinically trustworthy evidence. Existing medical RAG systems typically retrieve top-\(k\) chunks according to item-wise relevance. Although this design improves recall, it does not explicitly optimize whether the selected evidence set is compact, sufficient, and decision-critical. In this paper, we study medical evidence-grounded QA from a different perspective: instead of retrieving evidence without optimization, the evidence-grounded medical QA system should identify a compact sufficient subset of high-density evidence snippets. We propose **MEGA**, a gain-aware framework for compact supporting medical evidence selection. MEGA first expands clinical queries into complementary subqueries and performs hybrid retrieval to construct a recall-oriented candidate evidence pool. It then introduces hidden-state **Information Gain Scoring**, which uses a frozen LLM to estimate whether each candidate snippet contributes new answer-relevant information beyond surface relevance. Finally, MEGA formulates evidence selection as a budgeted utility maximization problem and proposes an **FPTAS selector** to identify a compact evidence subset under an explicit token budget. We further construct two evidence-grounded medical QA benchmarks, CRC-EvidenceQA and Med-EvidenceQA, to evaluate both answer quality and evidence grounding. Across three LLM backbones and five medical RAG baselines, MEGA consistently achieves the best results, improving over the second-best baseline by \(8.8\%\) on average in answer quality and 38.8\% on average in evidence F1. Ablation studies and blinded clinical expert evaluation further validate its robustness and clinical relevance.

Orthogonal parameter-efficient fine-tuning adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in which adaptation occurs and the transformation applied within that subspace. This paper introduces LOFT, a low-rank orthogonal fine-tuning framework that explicitly separates these two components. By viewing orthogonal adaptation as a multiplicative subspace rotation, LOFT provides a unified formulation that recovers representative orthogonal PEFT methods, including coordinate-, butterfly-, Householder-, and principal-subspace-based variants. More importantly, this perspective exposes support selection as a central design axis rather than a byproduct of a particular parameterization. We develop a first-order analysis showing that useful adaptation supports should be informed by the downstream training signal, motivating practical gradient-informed support selection strategies. Across language understanding, visual transfer, mathematical reasoning, and multilingual out-of-distribution adaptation, LOFT recovers principal-subspace orthogonal adaptation while gradient-informed supports improve the efficiency–performance trade-off under matched parameter, memory, and transform budgets. These results suggest that principled support selection is an important direction for improving orthogonal PEFT.

In natural scenes, light sources and occlusions from scene geometry create spatially varying illumination, including brightness gradients, cast shadows, and local color shifts that shape how every object appears. A less explored aspect of diffusion-based object compositing is whether an inserted object can adapt to this local illumination at the desired location. The core challenge to achieve this is the scarcity of large-scale training data capturing how object appearance should adapt to location-dependent illumination. We present LOCO, a data augmentation framework for LOcal light-aware object COmpositing that leverages publicly available monocular videos as illumination sources. We treat each video frame as a virtual spotlight anchored at its camera pose, so that viewpoint variation across a video yields diverse light directions. With controllable beam shape, color, and intensity, this design enables large-scale generation of training data for placement-dependent illumination on the fly. We also introduce LOCO-bench, a benchmark of physically captured composites under spatially varying illumination, where the same object is placed at multiple locations within each scene. Experiments on Laval Indoor SV HDR and LOCO-bench show that LOCO outperforms prior methods in local illumination adaptation while preserving object identity.

We propose LEGO, a budget-aware Dense-to-MoE methodology that converts pretrained vision-language models into efficient FFN-MoE variants under a target architectural budget $((P_{total},P_{active}))$. Our study is motivated by a counter-intuitive recovery pattern: fixed activation ratios that work well for some dense backbones can degrade sharply on others under the same recovery recipe, indicating that raw sparsity alone is an unreliable design rule. Through controlled recovery experiments across VLM families and scales, we identify the activated-FFN-to-hidden ratio $(D_I/D_H)$ as a backbone-comparable structural factor and summarize empirical sizing rules for avoiding severe bottlenecks while limiting diminishing returns. LEGO operationalizes these rules through a discrete budget-aware search over Split, Upcycle, and Hybrid constructions, and introduces a moment-matching scaling factor to reduce the initialization scale shift caused by sparse FFN aggregation. Finally, we use a two-stage multimodal recovery recipe that first stabilizes the sparse LLM with the vision tower frozen, then performs joint fine-tuning to recover the full VLM. Under matched data and training protocols, LEGO improves Dense-to-MoE recovery quality and turns costly blind architecture search into a small set of rule-guided candidates. Codes can be found in supplementary materials.

We ask whether agentic AI systems built for software engineering transfer to realistic hardware engineering. Existing hardware LLM benchmarks isolate sub-tasks but none jointly requires repository navigation, hierarchy-aware localization, Electronic Design Automation (EDA) executable verification, and maintenance-style patching. We introduce **Phoenix-bench**, a synchronized corpus of 511 verified Verilator instances from 114 GitHub repositories, each shipped with the developer patch, design-flow labels, fail-to-pass and pass-to-pass testbenches, and a Docker-pinned EDA environment so resolved-rate differences reflect agent behavior rather than toolchain availability. Using Phoenix-bench we run a uniform evaluation of four commerical agents and eight open-source agentic structures across four LLM backbones, plus two diagnostic interventions (file-level oracle localization and one round of testbench-log feedback). Three findings emerge. **Software and hardware are fundamentally different engineering tasks:** the same agent loses 37\% to 58\% from SWE-bench Verified to Phoenix-bench because hardware bugs propagate across parallel instantiated modules through signal flow rather than along a software-style call graph, and software-tuned agents stop at the symptom file instead of tracing back through the instantiation chain. **Failures concentrate on design control-flow / Finite State Machine bugs, verification testbench bugs, and hard cases** that demand cross-hierarchy signal-flow tracking and coordinated multi-file edits. **Localization granularity matters far more than localization itself:** a perfect file-level oracle yields only $+1.4$\% because the agent then breaks files that did not need editing, while a single round of test case feedback lifts resolved rate by $42$\% to $45$\% because the test case tells *where* the bug is and *what* the fix has to look like.

Large language model (LLM)-driven agents are proposed for a wide range of applications. As scenarios become increasingly composite, a graph-structured multi-agent system (MAS) offers a promising solution due to the orchestration of various skills. To architect a reasonable underlying workflow, recent advances mostly investigate two structures: sequential topology and decentralized topology. The former constrains the structure into a directed acyclic graph for multi-step executions but lacks sufficient scalability, while the latter leverages node-wise subgraphs for knowledge aggregation with synchronous parallelization but lacks long-term planning. Therefore, our key insight is that their strengths are mutually complementary. Driven by this motivation, we introduce step-aware hybrid topology for a MAS, where sequential connections support inter-step ordered planning and decentralized connections promote intra-step perspective integration. Concretely, to effectively coordinate different structural components, we clarify the corresponding topological definition and the protocols for step-wise serialization and parallelization. Subsequently, to dynamically refine desired structures, we introduce the parameterized distribution of a hybrid topology, which is initialized by LLM-driven graph planning. Eventually, to further reduce token consumption and time complexity, we supplement the topological density and length normalization for end-to-end learning. Extensive experiments demonstrate that the hybrid topology outperforms single-form topology in 90.4\% of tasks, our agentic initialization improves learning in 88.8\% of scenarios, proposed normalizations reduce token consumption by 20\%$\sim$30\% and time consumption by 7\%$\sim$13\% with a slight utility fluctuation. The code is available at https://anonymous.4open.science/r/HTAS-D107.

Quantization is a fundamental tool used to compress datasets, neural network weights, and memory usage in a range of computational tasks. Many downstream applications of vector quantization perform inner products with arbitrary inputs. This motivates the study of inner product aware quantization schemes that approximately preserve inner products with unseen vectors -- in contrast to simply minimizing the mean-squared error. In this work, we formulate objectives that capture natural desiderata and develop adaptive and unbiased quantization methods that approximately preserve inner products with worst-case and average case inputs. An analysis of these objectives shows a tight connection with the well-studied notion of Adaptive Stochastic Quantization (ASQ). We develop provably fast exact and approximate algorithms for our objectives. Our theoretical results inspire efficient practical algorithms that perform well across a variety of workload distributions. They also lead to practical algorithms for standard ASQ which are 2-10$\times$ faster than prior state-of-the-art methods while maintaining quality. These theoretical and empirical results contribute towards making adaptive quantization techniques more efficient and tractable in practical settings.

Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT uniformly fits all samples—including those with low likelihood under the base model—which can disproportionately drive training updates toward overfitting specific samples rather than learning the target behavior. Moreover, adapting to these unlikely samples induces substantial policy shifts that degrade prior capabilities. Existing methods mitigate this by filtering, regenerating, or down-weighting low-likelihood data. In doing so, they often suppress precisely the novel behaviors the base model has yet to learn. We propose InfoSFT, a principled weighting scheme for the SFT objective that concentrates learning signals on maximally informative, medium-confidence tokens—those neither overly familiar to the base model nor too unlikely to cause instability. Requiring only a one-line modification to the standard token-wise loss, InfoSFT demonstrably improves generalization over vanilla SFT and likelihood-weighted baselines across math, code, and chain-of-thought tasks with diverse model families, while better preserving pre-existing capabilities.

Key-value (KV) caches are essential for efficient Large Language Model (LLM) inference, but their memory footprint grows linearly with context length and batch size. Low-bit KV-cache quantization reduces this footprint, yet uniform quantization is vulnerable to high-magnitude outlier channels, while outlier-aware mixed-precision methods often introduce extra buffers, indexing, or channel permutation that weakens their system-level benefit. This paper presents InQuant, an in-place mixed-precision KV-cache quantization method that preserves salient outlier channels without changing the physical 4-bit packed layout. The key observation is that selected low-saliency channels near outliers can tolerate small approximation error; InQuant therefore reuses their storage slots to hold the extra 4-bit nibble needed by 8-bit outlier values. To make this layout practical, InQuant combines sampling-based channel saliency estimation, saliency-aware neighbor-slot reuse, stride-based handling for adjacent outlier groups, and descriptor-guided marker recovery during dequantization. Across six LLMs and long-context workloads, InQuant reaches a fixed 4.0$\times$ physical KV-cache compression ratio, preserves accuracy close to strong mixed-precision baselines, and reduces quantization/dequantization latency by 2.2$\times$--3.4$\times$ compared with representative outlier-aware methods.

Remote sensing imagery supports diverse visual tasks, such as object detection and semantic segmentation, but these tasks vary across scenes, imaging modalities, and target objects. Since many remote sensing scenarios lack sufficient annotations, conventional supervised learning is often difficult to apply, motivating in-context learning as a flexible alternative.We present an in-context learning framework for remote sensing visual tasks, where a new task is specified by a single annotated example and applied to unseen images without retraining at inference time. Built upon diffusion models, our framework establishes target-reference associations through cross-attention and transfers the structural relationship between the reference image and its annotation to produce task-specific predictions. Unlike natural images, remote sensing objects are often small and provide weak semantic cues in early diffusion steps, making semantic alignment between target and reference images difficult. We address this limitation with a semantic-aware cross-attention that combines semantic and fine-grained details for more accurate cross-image matching. Remote sensing objects also appear at arbitrary orientations, causing large appearance variations and unstable in-context transfer. To improve robustness, we introduce a rotation-robust learning strategy that reduces sensitivity to orientation changes. Experiments show that our method achieves strong one-shot performance, establishing a flexible paradigm for adapting remote sensing models to diverse visual tasks.

We study the problem of learning in multi-player general-sum Markov games. In the simulator setting, where the learner can sample the next state conditioned on an arbitrary state action pair, the previous best-known upper bound of the sample complexity for learning an $\varepsilon$-approximate coarse correlated equilibrium (CCE) is $\widetilde{O}(H^4S\sum_{i=1}^m A_i/\varepsilon^2)$ (Li et al., 2022), where $H$ is the horizon, $S$ is the number of states, and $A_i$ denotes the number of actions for the $i$-th player. This work improves the upper bound to $\widetilde{O}(H^4S\max_{i\in[m]} A_i/\varepsilon^2)$, matching the lower bound of $\Omega(H^4S\max_{i\in[m]} A_i/\varepsilon^2)$ (Li et al., 2022). In the online setting, in which the learner can only sample a trajectory, the previous best-known sample complexity upper bound for learning CCE in multi-player general-sum Markov games is $\widetilde{O}(H^6S\max_{i\in[m]} A_i/\varepsilon^2)$ (Song et al., 2021; Jin et al., 2024; Mao et al., 2022). In this work, we improve this to $\widetilde{O}(H^5S\max_{i\in[m]} A_i/\varepsilon^2)$. To our knowledge, this is the tightest upper bound that breaks the curse of multi-agency. The core of our algorithmic design and analysis is the new gap decomposition and, in particular, a bandit algorithm with a high-probability empirical variance regret bound, which might be of independent interest.

Modeling Irregular Multivariate Time Series (IMTS) poses significant challenges due to asynchronous sampling and data sparsity. While existing methods focus on handling temporal irregularity after encoding, the tokenization stage itself remains underexplored. We propose IMTS-Tokenizer, a time aware tokenization framework built on the Irregular-time-aware Module (IRAM), which employs learnable temporal anchors and Gaussian-kernel attention to aggregate observations while preserving temporal information. To improve robustness under sparse and asynchronous sampling, the framework further incorporates Relative Time Feature (RTF) for pre-aggregation temporal encoding, Variable-Specific Anchor Initialization (VSA) for data-aligned anchor placement, anchor regularization for stable training, and multi-scale modeling. Experiments on four benchmarks demonstrate state-of-the-art (SOTA) performance, with the best results on seven out of eight metrics and statistically significant aggregate gains.

Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in flat Euclidean space, treating them as independent, orthogonal dimensions. Concepts, however, are highly structured and organized in semantic hierarchies. To resolve this mismatch, we propose Hyperbolic Concept Bottleneck Models (HypCBM), a post-hoc framework that grounds the bottleneck in this structure by reformulating concept activation as asymmetric geometric containment in hyperbolic space. Rather than treating entailment cones as a pre-training penalty, we show they encode a natural test-time activation signal: the margin of inclusion within a concept's entailment cone yields sparse, hierarchy-aware activations without any additional supervision or learned modules. We further introduce an adaptive scaling law for hierarchically faithful interventions, propagating user corrections coherently through the concept tree. Empirically, HypCBM rivals post-hoc Euclidean models trained on 20$\times$ more data in sparse regimes required for human interpretability, with stronger hierarchical consistency and improved robustness to input corruptions.

Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling. We revisit this design from a frequency-domain perspective. Robot action trajectories are highly smooth, with most energy concentrated in a few low-frequency discrete cosine transform modes. Under this structure, we show that the error of the optimal denoiser is bounded by the low-frequency subspace dimension and residual high-frequency energy, implying that denoising error saturates after very few reverse steps. This also suggests that action denoising requires a much simpler denoising model than image generation. Motivated by this insight, we propose Hydra-DP3 (${\bf HDP3}$), a pocket-scale 3D diffusion policy with a lightweight Diffusion Mixer decoder that supports two-step DDIM inference. Our synthetic experiments validate the theory and support the sufficiency of two-step denoising. Futhermore, across RoboTwin2.0, Adroit, MetaWorld, and real-world tasks, HDP3 achieves state-of-the-art performance with fewer than 1\% of the parameters of prior 3D diffusion-based policies and substantially lower inference latency.

Neural surrogates promise large speedups over classical solvers for physical dynamics but fail silently at sharp dynamical events such as shocks, fronts, and contact. We present hybrid neural world models for physical dynamics: a recipe for training and deploying multi-horizon surrogates in physical state space, where a single network with continuous horizon conditioning is trained with direct supervision against textbook reference solvers to predict any future state at horizon $T$ in one forward pass. Although no part of the training data, loss function, or architecture supervises discontinuity location, the trained surrogate encodes it implicitly, recoverable from its forward passes alone as a per-trajectory error map that concentrates on shocks, fronts, and contacts, and stays small elsewhere. The map is competitive with or better than standard label-free baselines including deep ensembles, learned error heads, gradient-magnitude indicators, and locally-adaptive conformal prediction, while using only a single trained network and requiring no calibration set or governing-equation knowledge. The recipe supports two operating points. Mode 1 runs the surrogate alone for maximum throughput, with same-hardware CPU speedups of $26\times$ to $72\times$ against textbook solvers on the PDE environments. Mode 2 uses the error map to gate a reference-solver fallback, deferring uncertain trajectories and roughly halving the surrogate's residual error at the default operating point. The recipe applies without modification across reaction-diffusion, compressible Euler, and rigid-body collision dynamics.

Diffusion models have demonstrated strong performance in time series modeling due to their ability to progressively capture complex data distributions through iterative denoising. However, existing approaches struggle with frequency-sensitive denoising, high-frequency reconstruction and balancing global trends with local dynamics. To address these limitations, we propose \textbf{HyFAD}, a \textbf{Hy}brid time-frequency \textbf{D}iffusion model with \textbf{F}requency-\textbf{A}ware embedding for time series imputation. Built upon the DDPM paradigm, HyFAD adopts a coupled time-frequency diffusion framework, in which the reverse denoising proceeds sequentially from the time domain to the frequency domain, enabling coarse-to-fine generation. Specifically, the time-domain diffusion process captures low-frequency global trends, while the frequency-domain diffusion process refines high-frequency spectral components. We further introduce a frequency-aware step embedding that exploits the relationship between diffusion steps and spectral components, providing step-dependent spectral guidance and facilitates more accurate band-wise reconstruction. Extensive experiments on multiple benchmark datasets demonstrate that HyFAD achieves state-of-the-art performance. Our source code is available at \url{https://anonymous.4open.science/r/HyFAD-0C21/}.

For graph node classification, calibrated class probabilities are need when confidence scores, usually the maximum predicted class probability, are used to rank prediction, defer uncertain nodes to human review or control risk. Existing post-hoc calibrators either apply one global temperature or use graph-awared modules without a derived strctural form. We study node-level calibration for graph node-classification problem under structural heterogeneity. Our first results show that a logit-only temperature rule is insufficient when nodes with identical logits but different local homophily require different optimal temperatures. We then analyze a population-concentration contextual stochastic block model with Gaussian features and a one-layer linear GCN. Under equidistant class means, the Bayes posterior over class-template scores is a temperature-scaled softmax whose inverse temperature is governed by homophily-dependent signal strength. In the positive-signal homophilic regime, the resulting temperature decreases approximately with normalized local homophily. This law motivates Homophily-aware Temperature Scaling (HoTS), a simple post-hoc calibrator that assigns each node a positive scalar temperature from entropy-based logit concentration and estimated local homophily. HoTS has three parameters, preserving class, and learn the strength of the structural correction from calibraion data. Across 18 node-classification benchmarks, two GNN backbones, and eight calibration baselines, HoTS achieves the best mean Expected Calibration Error (ECE) of $4.66\%$, the best average rank, and the strongest confidence ranking in selective classification.