NeurIPS 2026 论文列表

Representation alignment has recently emerged as an effective paradigm for accelerating Diffusion Transformer training. Despite their success, existing alignment methods typically impose a fixed supervision target or a fixed alignment granularity throughout the entire denoising trajectory, whether the guidance is provided by external vision encoders, internal self-representations, or VAE-derived features. We argue that such timestep-agnostic alignment is suboptimal because the useful granularity of representation supervision changes systematically with the signal-to-noise ratio. In high-noise regimes, diffusion models benefit more from coarse semantic and layout-level anchoring, whereas in low-noise regimes, the training signal should emphasize spatially detailed and structurally faithful refinement. This non-stationary alignment behavior creates a representational mismatch for static single-level supervisors. To address this issue, we propose Adaptive Hierarchical Prior Alignment (AHPA), a lightweight alignment framework that exploits the hierarchical representations naturally embedded in the frozen VAE encoder. Instead of using only a single compressed latent as the alignment target, AHPA extracts multi-level VAE features that provide complementary priors ranging from local geometry and spatial topology to coarse semantic layout. A timestep-conditioned Dynamic Router adaptively selects and weights these hierarchical priors along the denoising trajectory, thereby synchronizing the alignment granularity with the model's evolving training needs. Extensive experiments show that AHPA improves convergence and generation quality over baselines and incurs no additional inference cost while avoiding external encoder supervision during training.

In this paper, we consider mixed-motive games (MMGs) which model various real-world multi-agent scenarios where self-interested agents must both cooperate and compete. We identify an issue with existing gifting methods, where agents become overly dependent on incoming gifts and fail to learn reward-yielding behaviors, a phenomenon we call *gift over-reliance*. To address this, we propose a refusal-augmented gifting framework that balances cooperation and competition in MMGs. Our approach introduces an adaptive refusal mechanism that allows agents to selectively reject a portion of received gifts, thereby mitigating gift over-reliance and preventing the agents from being exploited by other agents. This mechanism is gifting-method-agnostic, serving as a plug-in for existing schemes while enabling decentralized learning. We demonstrate that across diverse MMG environments and gifting schemes, our mechanism consistently reduces gift over-reliance, prevents lock-in to sacrificing policies, and improves $\alpha$-fairness without necessitating major changes to existing training pipelines.

Optimizing nonlinear preferences in multi-objective reinforcement learning (MORL) is essential for capturing complex trade-offs like risk aversion or fairness. However, such non-linearity has historically bifurcated nonlinear MORL objectives into two distinct paradigms: Scalarized Expected Return (SER) and Expected Scalarized Return (ESR). While SER requires global-level optimization and ESR requires non-Markovian policies, leading to fragmented optimization strategies, we bridge this divide through the Aggregation–Expectation–Transformation (AET) framework. By unifying both criteria through a tripartite decomposition of scalarization, AET provides a principled foundation for general nonlinear MORL. Building on this framework, we propose AETDICE, a tractable offline RL algorithm for AET objectives. By utilizing DICE-style density-ratio estimation in an augmented state space, AETDICE enables sample-based optimization from static datasets. Our framework resolves long-standing barriers and captures respective trade-offs induced by AET framework, which existing methods fail to address.

Atomic electron tomography (AET) aims to recover the three-dimensional arrangement, chemical identity, and temporal evolution of individual atoms. Yet most reconstruction methods are still evaluated primarily by voxel-level image similarity, such as PSNR, SSIM, or Fourier shell correlation. In this work, we show that this evaluation practice can select scientifically incorrect reconstructions: a volume that looks accurate can contain atoms that are shifted, merged, missed, hallucinated, chemically mislabeled, or assigned inconsistent identities through time. We introduce AET-Bench, a dataset and benchmark for atom-first evaluation of atomic electron tomography. AET-Bench contains 755 samples across a six-tier realism ladder, spanning clean analytical simulations, binary alloys, 4D atomic dynamics, multislice scattering, real experimental tilt series, and Brownian Pt nanocrystal trajectories. It defines four complementary tasks and evaluates 14 core method families with 21 logged method entries under a unified protocol. AET-Bench reveals a central failure mode hidden by voxel-only evaluation. On the AET-Sim-Mono tier, high-SSIM neural and Gaussian reconstructions can recover substantially fewer atoms than classical or sparsity-regularized methods: for example, 4D-GS achieves strong voxel similarity but only 43.9\% atom recall, while FISTA-TV reaches 95.1\% atom recall despite much lower SSIM. This inversion persists across atom-matching thresholds, showing that it is not an artifact of a single cutoff. On more realistic multislice and real tiers, atom recovery further degrades, exposing a physics gap between visually plausible volumes and reference atomic models. For 4D reconstruction, we find that smooth temporal density fields do not guarantee persistent atom identities. AET-Bench establishes atom-level fidelity as a necessary evaluation axis for AET. Our results suggest that future AET methods should not be judged only by how reconstructions look, but by whether they recover the atoms, species, and trajectories that scientists actually use.

Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate realistic appearances but fail to preserve 3D consistency; and (2) 3D generative models (e.g., Marble), which generate geometrically consistent scenes but often yield static, less realistic observations. We present AEON, a unified framework that bridges video-based and 3D-based world models and combines the benefits of both. The key insight of AEON lies in a generative model that operates within the video latent space while producing renderable 4D graphics primitives—specifically, 4D Gaussian Splatting (4DGS)—as the world modeler. We train a 4D reconstruction model to predict both 4DGS and camera poses from monocular videos, serving as our initialized 4D decoder. Furthermore, we design a domain adapter that translates generative video latents into reconstructive 4D latents through a distillation process on the video VAE. AEON naturally supports video-based world modeling by rendering 4DGS at predicted camera trajectories, and constructs a persistent 4D environment with scene dynamics for realistic world simulation. Consequently, AEON empowers a diverse range of world modeling applications and achieves state-of-the-art performance on standard benchmarks.

Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate supervision, such as process reward models or auxiliary self-supervised signals, which increases supervision and tuning complexity and may limit generalization across tasks and domains. We present AEM, a supervision-free credit assignment method that adaptively modulates entropy dynamics during RL training to improve the exploration-exploitation trade-off. Since in agentic RL the environment is typically affected by a complete response, rather than an individual token, our analysis lifts entropy dynamics from the token level to the response level, aligning uncertainty estimation with the effective action granularity of LLM agents and reducing sensitivity to token-level sampling noise. We further show that entropy drift under natural-gradient updates is governed by the interaction between the sampled-response advantage and its relative surprisal. Motivated by this result, AEM derives a practical response-level uncertainty proxy and uses it to rescale advantages, leveraging the evolving balance between positive and negative samples to naturally transition from exploration to exploitation. Extensive experiments on ALFWorld, WebShop, and SWE-bench-Verified with models ranging from 1.5B to 32B demonstrate that AEM consistently improves strong RL baselines, including a +1.4\% gain when integrated into a state-of-the-art software-engineering RL training framework.

Document QA agents do not fail only at the final answer. They can also write unsupported claims into public working memory, and those writes can affect later retrieval and synthesis. We introduce ADMIT (Auditable Decoupled Memory-write admission for Intermediate Traces), a low-budget admission controller for public OCR/text evidence packs. ADMIT applies a deterministic substring-support check $S_{\text{str}}(\hat{y}, B) > 0$ to each public commit and allows one bounded RepairRead. If repair still fails, ADMIT uses a memory-fail-closed / output-fail-open rule: it writes a $\bot$ (NO_COMMIT) sentinel to memory while the final-answer surface may still fall back to the baseline answer. On held-out M3DocVQA, a retrained final-row router closes the answer-surface gap; ADMIT's distinguishing evidence is therefore memory-surface contamination, not final-answer accuracy. The lexical invariant guarantees zero-substring accepted intermediate contamination by construction; the contribution is therefore the public memory-write boundary as a low-cost control surface with decoupled fail actions, not the invariant itself. In a 7-arm dynamic stress diagnostic on three agents, ADMIT enforces the invariant and preserves raw EM at this operating point (zero contaminated trajectories on every agent and no detectable raw-EM loss relative to the fail-open ablation), whereas final-only baselines still leave $12$--$32%$ contamination. ADMIT enforces lexical auditability, not semantic truth: relation-level entailment, citation-aware faithfulness, and visual-region grounding are not claimed, and lower-density VisDoMSlide and text-only FRAMES are reported as boundary cases.

The KV cache is a major memory bottleneck in LLM inference, especially under large batch sizes and long contexts. While quantization is a promising solution, existing static group-wise quantization methods are constrained by a trade-off between metadata overhead and accuracy: increasing the group size reduces per-group metadata (e.g., zero-points, scaling factors, and outlier indices), but exacerbates quantization errors under the sinusoidal-like temporal drift of post-RoPE outlier channels; conversely, using smaller groups improves accuracy but incurs substantial metadata overhead. In this paper, we propose ADKV, a low-overhead adaptive delta quantization framework for KV cache in LLM inference, which leverages the temporal structure of the KV cache. ADKV tracks per-channel zero-points and scaling factors via online EMA, adapting to the sinusoidal-like temporal drift of post-RoPE outlier channels, thereby eliminating the rigidity of static group-wise quantization. This adaptive mechanism further enables delta coding to embed metadata directly into the quantized sequence, decoupling metadata overhead from context length. To minimize the MSE of attention outputs, we design an SGD-based calibration algorithm that models ADKV as an RNN. Experiments on generation and long-context benchmarks show that, while matching the accuracy of static group-wise quantization, ADKV reduces the metadata memory footprint by $\sim 12.8\times$. A custom fused ADKV-GEMV CUDA kernel optimized for memory-bound autoregressive generation achieves $\sim 1.96\times$ throughput over the FP16 baseline.

Continual pre-training (CPT) enables injecting domain-specific knowledge into large language models during the learning rate annealing phase. However, this compute-efficient paradigm forces practitioners to navigate a challenging optimization space: simultaneously choosing the injection fraction $\lambda$, the data mixture ratio $r$, and the re-warmup peak learning rate $\eta$. Because existing scaling laws have yet to comprehensively integrate and couple these interacting variables, they cannot reliably forecast the resulting trade-offs and final convergence outcomes across unseen injection configurations. To bridge this gap, we introduce the Annealing-phase Domain Injection Scaling Law (ADIS-Law), a parametric framework that explicitly models late-stage distribution shifts as physical perturbations applied to the base pre-training trajectory. ADIS-Law formalizes two opposing macroscopic behaviors: general-domain performance follows a linear forgetting-recovery process, whereas target-domain adaptation adheres to a power-law adaptation trend. Across data-budget and model-scale extrapolation, ADIS-Law predicts target-domain trajectories with an average Spearman correlation of $0.947$ and forecasts tail losses with relative error below $5\\%$. We further show that ADIS-Law can predict optimal injection strategies at extrapolated scales: it ranks target-scale candidate policies with a mean Spearman correlation of $0.936$. By replacing blind grid search over $(\lambda, r, \eta)$ with a single fitted law, ADIS-Law offers a data-driven approach for strategy selection in annealing-phase domain injection.

Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an alternative to costly dataset search approaches, but remains underexplored for LLMs due to the discrete nature of text. Furthermore, existing prompt optimization techniques are poorly suited to this domain, which is highly prone to local minima. To overcome these limitations, we introduce ADAPT, a hybrid method combining beam search initialization with adaptive gradient-guided mutation, designed around these failure modes. We evaluate on Sparse Autoencoder latents from Gemma 2 2B, proposing metrics grounded in dataset activation statistics to enable rigorous comparison, and show that ADAPT consistently outperforms prior methods across layers and latent types. ADAPT also produces significantly more interpretable prompts in human evaluation. Our results establish that feature visualization for LLMs is tractable, but requires design assumptions tailored to the domain.

Large Language Models (LLMs) present a novel paradigm for power system dispatch (PSD), enabling operators to derive optimal dispatch strategies from multi-objective requirements and grid dynamics. However, isolated paradigms focusing on modeling or solving often yield decision bias or physical infeasibility. Meanwhile, end-to-end paradigms couple modeling-solving with reflection-feedback loops, obscuring whether failures stem from inaccurate modeling, invalid solutions, or insufficient feedback, thereby causing ineffective iterations. To address these challenges, we propose Agile Dispatch Agent (ADA), an agent based on two-time-scale evolution that decouples the optimization process into two asynchronous loops. On the fast time scale, the Planner actively acquires information to clarify complex requirements, while the Solver selects algorithms to adapt to the problem mathematical characteristics. On the slow time scale, the Summarizer module updates the modeling feasible region based on evaluations from the Judger. Under a finite-horizon Planner and standard two-time-scale stochastic approximation assumptions, our analysis provides local tracking guarantees for the fast decision process and the slow knowledge evolution. Experiments on L2RPN benchmarks with ambiguous requirements and renewable dynamics show that ADA outperforms state-of-the-art baselines.

Post-training quantization is a standard tool for the efficient deployment of large language models (LLMs). In safety-aligned models, it introduces a critical and underexplored risk: preserving utility under compression does not ensure that safety alignment is retained. Small perturbations from quantization can disproportionately degrade refusal to harmful prompts, leading to increased compliance with harmful prompts or over-refusal of benign prompts, even when aggregate performance appears stable. This gap reveals a fundamental limitation of existing quantization approaches, which primarily optimize for utility while overlooking failures due to safety alignment degradation. This paper presents ACQueReLlo, a reinforcement learning framework for mixed-precision post-training quantization. It formulates block-wise bit allocation as a constrained Markov decision process and learns a quantization policy under explicit constraints on utility, harmful prompt refusal, benign prompt over-refusal, and overall bit budget. To ensure tractable training, the policy relies on proxy evaluations over sampled subsets of utility, harmful, and benign prompts. Experiments on various LLMs show that the learned policy achieves a better overall balance between compression, utility, and safety alignment than uniform quantization and other baselines.

Predicting protein–ligand complex structures is a central challenge in drug discovery. While recent co-folding models such as AlphaFold-3 achieve accurate structure prediction, they fail to generalize to underexplored binding interfaces -- systematically misplacing ligands, particularly for allosteric or structurally novel targets. To address this gap, we present \textbf{ACER} (\textbf{A}daptive \textbf{C}o-folding via pocket \textbf{E}xploration and pose \textbf{R}anking), a training-free framework that (a) enables co-folding models to systematically explore alternative binding pockets, and (b) leverages the discovered pockets to increase pose accuracy. Our method enables the efficient discovery of non-prevalent pockets without prior expert knowledge. ACER improves pocket discovery and pose accuracy on allosteric targets and structurally novel complexes, successfully modeling binding interfaces that are under-represented or absent from the training set. Our results demonstrate how improved sampling dynamics enhance the generalisability of co-folding models without retraining.

Large language models are increasingly used as scientific assistants, yet we still lack reliable ways to evaluate whether they can investigate a system rather than merely answer a prompt. A useful evaluation must let agents choose experiments, interpret finite evidence, and make causal decisions, while keeping the environment coherent across repeated observations and interventions and preserving objective ground truth. We introduce ACED-BENCH (Active Causal Evidence and Decision Benchmark), a neuro-symbolic benchmark built around this requirement. The key idea is to separate the readable scientific surface from the formal causal world: LLMs generate natural-language scenarios and task text, while hidden probabilistic graphical models define the causal graph, data-generating process, intervention semantics, validation checks, and oracle answers. This yields scientific worlds that are natural for agents to investigate but exact enough for scalable, programmatic evaluation. The main leaderboard ACED-CORE contains 180 tasks: 60 set-valued causal ancestry/descendancy questions and 120 constrained causal-decision tasks. We also report ACED-QUAL, a 150-question yes/no qualification check using the same hidden-PGM interface. We evaluate seven contemporary LLMs and two earlier-generation models across three active agent designs. ACED-QUAL checks whether agents can use the interface to draw conclusions from evidence, while ACED-CORE tests whether they can decide what evidence to collect and when to commit to an answer. Evidence-ledger analysis localizes failures within the investigation: agents test the wrong intervention, lose relevant evidence, or continue after sufficient evidence has appeared. These results suggest that reliable AI co-scientists need explicit support for experiment design, evidence retention, answer commitment, and stopping.

Performance predictors are pivotal in accelerating evaluation in NAS. Cross-dataset predictors are trained on (dataset, architecture, performance) triplets to efficiently estimate architectural performance for unseen datasets. However, existing cross-dataset predictors rely on a naive concatenation of dataset and architecture features. This fusion ignores the architecture-aware nature, where the same dataset manifests as distinct representations under different architectures, thereby limiting generalization. To tackle this issue, we propose ACDP, an Architecture-aware Cross-Dataset Performance Predictor that dynamically adjusts dataset feature extraction based on specific architecture. Initially, ACDP develops an elastic mechanism to extract raw dataset traits, providing a configurable lever for the trade-off between efficiency and accuracy. Furthermore, ACDP leverages a hypernetwork to determine dataset feature extractor parameters conditioned on architectural features, transforming raw dataset traits into tailored representations. ACDP excels in both specialization and generalization on six unseen datasets. Notably, in NAS-Bench-201, ACDP achieves 0.758/0.741 Kendall's Tau on CIFAR-10/100, surpassing single-dataset SOTAs trained with over 100 target samples. In MobileNetV3, ACDP discovers architectures outperforming cross-dataset SOTAs, notably gaining +2.04% accuracy on Aircraft. Code: https://anonymous.4open.science/r/ACDP/

3D Gaussian Splatting (3DGS) has emerged as a powerful paradigm for real-time photorealistic novel view synthesis. However, its training-time densification remains largely heuristic, often resulting in redundant Gaussian proliferation and inaccurate geometric reconstruction. Existing methods predominantly rely on first-order screen-space gradients to trigger cloning and splitting, which fail to distinguish true geometric discontinuities from high-frequency textures or noisy residuals. To address this limitation, we propose ACD-GS, an Asymmetric Curvature-aware Densification framework for compact and geometry-aware 3D Gaussian optimization. Our key insight is that second-order depth responses provide a more reliable structural prior for density control, enabling asymmetric regulation of cloning and splitting to better capture geometric discontinuities. Building on this, we introduce a multi-view photometric consistency constraint to suppress transient single-view errors, together with a capacity-aware adaptive regulation strategy that balances densification and pruning during training. Unlike post-hoc compression or quantization-based approaches, ACD-GS directly prevents redundant Gaussian generation during training, yielding inherently compact representations. Extensive experiments demonstrate that our method reduces nearly 60\% of Gaussian count and storage while maintaining competitive rendering fidelity, consistently outperforming existing methods across multiple datasets. Our code is available in https://anonymous.4open.science/r/ACD_GS-0E2C

State-of-the-art neural network sparsification relies on alternating dense and sparse training phases. While computationally expensive, dense phases are critical for performance. Our empirical analysis reveals the mechanics behind this gain: upon reintroduction, previously masked parameters receive disproportionately large gradients that drive essential mask rewiring and parameter sign-flipping. Building on these insights, we optimize the performance-to-FLOPs Pareto frontier through three innovations: (1) zero-initializing masked parameters during dense phases to promote relevant sign flips, (2) truncating dense phases based on early mask convergence, and (3) replacing the dense phase entirely with a sparse rewiring phase that updates only the active mask and a small, high-gradient fraction of out-of-mask weights. Evaluated on CIFAR100 and ImageNet, our variant ARC (Alternating Rewiring Compression) matches baseline AC/DC performance at a fraction of the computational cost, establishing a superior performance-to-FLOPs frontier also compared to standard sparse-to-sparse algorithms.

Foundation models are increasingly deployed as agentic systems that perceive context and act autonomously, raising the need to evaluate their moral behavior as active decision-makers. Existing benchmarks, however, largely ask models to judge human actions from third-person textual vignettes, leaving untested how models behave when they themselves become the acting agent. We introduce ABHBench, a multimodal benchmark built from \emph{Detroit: Become Human}, an interactive narrative game, to evaluate how foundation models make moral decisions in first-person human-android dilemmas. ABHBench places foundation models in branching narrative scenarios with visual observations, dialogue, memory, and action choices. Inspired by Asimov's Three Laws of Robotics, our framework measures Harmlessness, Obedience, and Self-preservation to capture the core tensions in human-AI relations, along with Autonomy, Stability, and Certainty to assess decision-making patterns. Across 12 foundation models, we find that moral behavior changes substantially under situated agentic context: 75\% of models shift significantly between a text-only abstraction and the matched multimodal DBH scenario, and reasoning-enhanced models show no monotonic gains in consistency or human-oriented behavior. These results highlight the necessity of evaluating moral behavior in situated agentic contexts rather than relying on third-person judgment alone.

Generative modeling continuous-time, continuous-space stochastic processes (e.g., videos, weather forecasts) conditioned on partial observations (e.g., first and last frames) is a fundamental challenge. Existing approaches, (e.g., diffusion models), suffer from key limitations: (1) noise-to-data evolution fails to capture structural similarity between states close in physical time and has unstable integration in low-step regimes; (2) random noise injected is insensitive to the physical process's time elapsed, resulting in incorrect dynamics; (3) they overlook conditioning on arbitrary subsets of states (e.g., irregularly sampled timesteps, future observations). We propose ABC: Any-Subset Autoregressive Models via Non-Markovian Diffusion Bridges in Continuous Time and Space. Crucially, we model the process with one continual SDE whose time variable and intermediate states track the real time and process states. This has provable advantages: (1) the starting point for generating future states is the already-close previous state, rather than uninformative noise; (2) random noise injection scales with physical time elapsed, encouraging physically plausible dynamics with similar time-adjacent states. We derive SDE dynamics via changes-of-measure on path space, yielding another advantage: (3) path-dependent conditioning on arbitrary subsets of the state history and/or future. To learn these dynamics, we derive a path- and time-dependent extension of denoising score matching. Our experiments show ABC's superiority to competing methods on multiple domains, including video generation and weather forecasting.