NeurIPS 2026 论文列表

Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irregular interactions remains underrepresented. Although recent world models achieve impressive realism on existing benchmarks, they primarily focus on simulating common physical interactions. This raises a central question: Do world models internalize and generalize the physical principles? In this work, we introduce Tailor-Bench, a benchmark to systemically evaluate this question through the lens of visual world modeling on tool-using interactions. Our benchmarks features three scenario modes (regular, unconventional and impossible), and two settings (predictive and descriptive) under a unified evaluation protocol. Our experimental results reveal a clear long-tail gap in visual world modeling: Performance consistently degrades from Regular to Unconventional and Impossible scenarios, indicating limited generalization beyond common interactions. Failure analysis further shows that models rely on superficial visual patterns, where image models fail to realize correct state changes, and video models additionally suffer from temporal inconsistencies. These limitations persist even with explicit outcome descriptions: Models often revert to familiar patterns in descriptive settings and fail to infer correct outcomes in predictive settings. By exposing systematic failures under long-tail scenarios, Tailor-Bench highlights the need for world models that understand object attributes, causal dynamics, and constraint-aware interactions. We further introduce Tailor-Evaluator-8b, a specialized auto-evaluator trained with structured reasoning supervision, which achieves 0.88 human correlation for scalable evaluation of long-tail visual world modeling.

Dual-system Vision-Language-Action (VLA) models improve real-time robotic control by pairing a slow, reasoning-capable generalist with a fast specialist action expert. However, existing methods invoke the generalist at a fixed frequency, ignoring the fact that decision-making complexity varies throughout a rollout. This static strategy wastes computation in easy phases and can delay intervention when unexpected scene changes require renewed high-level reasoning. We propose TUD (Triggering generalist reasoning via predictive Uncertainty for Dual-system VLA), an adaptive inference framework that selectively skips unnecessary generalist calls. TUD measures the cross-step dispersion of action re-predictions at the upcoming chunk slot, computed from the specialist's existing forwards under the cached generalist context, as a predictive uncertainty signal. This signal captures how much the future action plan shifts as new observations arrive, enabling TUD to invoke the generalist only when the cached plan becomes unreliable, and separates success from failure more reliably than prior uncertainty signals. The signal needs no manually labelled phase boundaries or auxiliary uncertainty model, and is computed from forwards the architecture already runs. On VLA-Arena, TUD finds a more favorable cost--success trade-off than non-adaptive baselines, tracing an entire operating curve as a single threshold is varied, and substantially reduces VLM calls at matched success rate. Our results suggest that predictive uncertainty provides a practical criterion for adaptive reasoning in efficient VLA control.

Generative recommendation (GR) aligns with advances in generative AI by casting next-item prediction as token-level generation rather than score-based ranking. Most GR methods adopt a two-stage pipeline: (i) \textit{item tokenization}, which maps each item to a sequence of discrete, hierarchically organized tokens; and (ii) \textit{autoregressive generation}, which predicts the next item's tokens conditioned on the tokens of user's interaction history. Although hierarchical tokenization induces a prefix tree (trie) over items, standard autoregressive modeling with conventional Transformers often flattens item tokens into a linear stream and overlooks the underlying topology. To address this, we propose TrieRec, a trie-aware generative recommendation method that augments Transformers with structural inductive biases via two positional encodings. First, a \textit{trie-aware absolute positional encoding} aggregates a token's (node's) local structural context (\eg depth, ancestors, and descendants) into the token representation. Second, a \textit{topology-aware relative positional encoding} injects pairwise structural relations into self-attention to capture topology-induced semantic relatedness. TrieRec is also model-agnostic, efficient, and hyperparameter-free. In our experiments, we implement TrieRec within three representative GR backbones, achieving notably improvements of 8.83\% on average across four real-world datasets.

Clinical drug development is high stakes. Small statistical errors propagate into trial design, participant exposure, and stop/advance decisions. As agents are increasingly used to support analysis and decision-making, more robust evaluations of their capabilities in clinical domains are needed. We introduce TrialAgentBench, a public benchmark in which agents must analyse participant-level evidence, choose defensible estimands and methods, quantify uncertainty, diagnose assumption failures, and carry those analysis decisions into downstream drug-development decisions. TrialEvalBench contains 400 patient-level analysis tasks across design, assumption, and context tiers. TrialDevBench contains 20 sequential development programmes across five scenario worlds, each starting from a confounded 10,000-patient observational extract and proceeding through asset nomination, endpoint and sample-size design, deterministic phase trials, phase analysis, and stop/advance decisions. The release spans 420 evaluated tasks or programmes, 528,660 simulated subjects, 77.6 million public tabular records, and 1.46 billion row-variable cells. Agents see only participant-facing data; grader-only files contain cell-appropriate targets, deterministic phase state, and scoring code. On TrialEvalBench, GPT-5.4 completes all 400 items but matches the required estimand/method class (e.g., log-HR versus RMST or risk-difference targets) for only 215/400 and produces an acceptable next-trial sample-size plan for 161/400. On TrialDevBench, GPT-5.4 and Claude Opus 4.7 complete all 60 seeded development programme runs per model, yet frequently nominate the wrong initial asset under confounding and choose evidence-supported stop/advance timing in fewer than one-third of programmes. Together, the two suites make clinical-trial decision quality measurable. Current agents can effectively execute familiar analyses, but fail to make the decisions those analyses exist to support.

Autoregressive (AR) video diffusion has emerged as a leading paradigm for efficient video generation, yet its practical deployment remains bottlenecked by the trade-off between generation quality and inference efficiency. We attribute this bottleneck to three error sources in AR rollouts: the base model error, the train–inference distribution mismatch, and the upstream error propagation. Building on this decomposition, we derive closed-form upper bounds on the per-step and cumulative errors, providing a principled mechanism for jointly optimizing generation quality and inference efficiency. Guided by this analysis, we propose **TriTD**, a **Tri**-Partite **T**rajectory–**D**istribution co-optimized distillation framework with three complementary modules that each target a distinct error term in the bound. First, for ODE initialization, we adopt a Next-Node Trajectory Distillation (NTD) objective and prove a strictly tighter error bound than conventional consistency distillation, reducing the base model error at its source. Second, we introduce Chunk-Graded Noising (CGN), a monotonically non-decreasing per-chunk noising schedule that provably narrows the train–inference noise mismatch and removes redundant KV Cache updates, yielding substantial speedups at no quality cost. Third, we propose Orthogonal-Parallel DMD (OP-DMD), a distribution-matching loss that preserves the original DMD gradient direction while explicitly suppressing unsupervised off-axis drift in the orthogonal subspace, improving both training stability and final generation quality. Extensive experiments show that TriTD consistently surpasses state-of-the-art baselines in visual quality while reaching a real-time throughput of **26.8 FPS** on a single H100 GPU, delivering a balanced quality-efficiency solution for interactive streaming video generation.

To ensure a formal guarantee that fully human-written text streams are *not falsely accused* as machine-generated text (MGT), the online betting framework (e-values) has been successfully applied on various existing detectors. However, current two-sample e-value methods fail in two real-world application scenarios: the false positive rate (FPR) is often out of control and the test power drops drastically when (1) the reference domain is similar but not exactly same as test domain (cross-domain), or (2) proxy model of detector is outdated compared to the modern source model. We identify the root cause as an online calibration dilemma: two-sample optimization and betting relies on a null-calibrating offset that is unidentifiable from unlabeled test streams under shift. We resolve this with a triple-sample betting framework (TriBet) that conduct online MGT detection as relative testing against both human and machine references using a witness score, and introduces a conformal test-inclusive domain-shift betting strategy to achieve FPR control without fragile online calibration. We show that TriBet is a level-$\alpha$ sequential test with asymptotic power one, and characterize its expected stopping time. Empirically, we evaluate on 15 source LLMs, 8 proxy models and mixed-document streams, TriBet consistently delivers faster and more powerful detection than both oracle and online betting baselines while keeping FPR strictly controlled.

Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context processing, the ability to handle multimodal inputs, and structured multi-turn interactions with tool calling capabilities. As a result, their context exhibits structure that can carry different importance along three key axes: temporal recency to the current turn, modality such as text or image tokens, and semantic role such as user queries, tool calls, observations, or reasoning. These axes capture distinct token behaviors and lead to different sensitivities to KV-cache compression. However, existing KV-cache quantization methods are typically homogeneous or exploit only heterogeneity on a single dimension, such as temporal proximity or modality, overlooking the interactions among them. To this end, we introduce TriAxialKV, a novel mixed-precision KV-cache quantization scheme that assigns each token a triaxial tag, calibrates per-tag sensitivity, and allocates INT2/INT4 bitwidths under a fixed memory budget. We implement TriAxialKV as an end-to-end serving system, comprising calibration, mixed-precision quantization and memory management, and custom fused Triton decode kernels. When using Qwen3-VL-32B-Thinking as a computer-use agent operating the OSWorld, TriAxialKV matches the accuracy of SGLang with BF16 KV cache while supporting 4.5$\times$ KV cache size and achieving 30\% higher end-to-end throughput, when running on real GPU systems.

Recent video diffusion models achieve strong visual quality and temporal coherence, but still lack coordinated control over scene layout, customized subject identity, and camera/subject motion. We study controllable video generation from three prompts: a first-frame scene image, 3D-aware multi-view subject references, and a motion-driving signal. This setting is challenging because background regions are often trackable under camera motion, while foreground subjects can rotate, self-occlude, and reveal new regions that require identity-consistent appearance. We introduce Tri-Prompting, a video diffusion framework that combines multi-view subject conditioning with dual-conditioned motion control. Tri-Prompting uses XYZ tracking points for visible background motion and low-resolution RGB proxies for foreground subject pose, allowing the model to recover fine appearance from multi-view references while retaining flexibility for plausible subject-scene interactions. An inference-time ControlNet scale schedule further balances motion controllability and visual realism. We evaluate Tri-Prompting against specialized baselines: DaS for motion reconstruction and Phantom for subject-driven generation. Tri-Prompting achieves competitive or improved reconstruction quality, stronger multi-view identity preservation, and better 3D consistency, while enabling 3D-aware subject insertion and in-scene manipulation.

Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Trellis4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting it from image-to-3D to video-conditioned 4D generation. Our design arises from two key questions: (a) how to enable Trellis2's frame-local attention to share information across frames while preserving its pretrained quality on rare cases such as transparent objects and inner surfaces, and (b) how to inject temporal information into a purely 3D positional encoding without breaking pretrained capabilities. We address (a) with a sliding-window cross-frame attention and anchor on the first frame. The first frame is generated by the base Trellis2 model and injected into our model, letting it inherit Trellis2's quality in rare cases through cross-frame attention. We address (b) with a 4D temporal encoding that repurposes redundant low-frequency spatial RoPE bands for time, extending the encoding from 3D with no additional parameters. Extensive experiments show the effectiveness of Trellis4D for high-quality dynamic mesh generation on ActionBench and our own challenging complex dynamics set.

Data augmentation improves visual recognition by exposing models to synthetic training examples that encourage generalization beyond the observed data. Mixed-sample methods extend this idea by combining multiple images. However, existing approaches either mix only pairs of images or rely on fixed small layouts, limiting control over source count, visible area proportions, and induced supervision. We propose TreemapMix, a distribution-controlled multi-image augmentation that samples source weights from a Dirichlet distribution and assigns them to area-proportional regions using a treemap partition. The resulting known region areas support two complementary objectives. TreemapMix with soft cross-entropy (SCE) treats areas as soft class-probability targets, while TreemapMix with a Plackett-Luce (PL) objective converts areas into ordinal supervision. On ImageNet-1K under a matched training protocol, TreemapMix-SCE achieves substantially lower calibration error than evaluated mixed-sample baselines, while TreemapMix-PL achieves the strongest Top-1 accuracy. Transfer experiments on object detection and instance segmentation suggest that TreemapMix-pretrained features remain useful beyond classification. These results show that controlled multi-image composition can expose the same region-area information as either probability-matching or rank-matching supervision.

Many prediction tasks evaluate a tree ensemble on row groups that share feature values: discrete-time survival models expand each patient into $G$ time steps, click-through-rate models score each item in a search session, and scenario analyses vary a few inputs while keeping others fixed. Standard tree-ensemble inference treats each row independently, ignoring this input-side correlation. We instantiate partial evaluation for grouped tree-ensemble inference: constant features are static, varying features dynamic. The algorithm walks each tree once per group, partitions a row bitmask at varying splits, and skips empty subtrees via an unsplit shortcut. We prove a structural work decomposition: per-tree work splits into the constant-projected subtree size $|T_c|$, $G$ leaf writes, and a predicate-mask provisioning cost $Q$. For the trace evaluator, per-row work approaches $(d_v+1)/(d+1)$ as $G \to \infty$, giving asymptotic speedup $1/(1-\bar\rho_G)$. Empirically, TreeWalker delivers ${\sim}3\times$ algorithmic speedup over a row-independent traversal at the reference model size ($T{=}500$, $L{=}8$; $G{=}16$ for SUPPORT/FLCHAIN and empirical groups for Expedia), rising to $6.8$--$7.8\times$ at $G{=}128$ on the survival datasets. For f64 models, outputs match treelite GTIL up to tree-ordering roundoff; for f32 models, TreeWalker's f64 leaf accumulation is close to a Kahan-compensated reference than native f32 on $99.98\%$ of rows, with the remaining $0.02\%$ tied.

To lower the expertise barrier in machine learning, the AutoML community has focused on the CASH problem, which jointly automates algorithm selection and hyperparameter tuning. While traditional methods like Bayesian Optimization (BO) struggle with cold-start issues, Large Language Models (LLMs) can mitigate these through semantic priors. However, existing LLM-based optimizers generalize poorly to high-dimensional, structured CASH spaces. In this paper, we propose LB-MCTS, a trajectory-structured optimization framework that uses a Monte Carlo Tree Search tree as a shared state for algorithm selection, hyperparameter refinement, and BO–LLM proposer synergy. Within this shared state, BO provides algorithm-specific surrogate modeling for quantitative search, while the LLM exploits path-aware selective memory to generate semantic proposals and reflections. As the surrogate model improves, a reliability-aware proposer policy adaptively shifts from LLM-driven to BO-driven proposals within a unified search trajectory. Experiments on 104 AMLB datasets demonstrate that LB-MCTS consistently outperforms BO-based, LLM-based, and hybrid baselines.

Tree-sliced distances have emerged as scalable alternatives to Sliced Wasserstein distances by projecting probability measures onto tree metric spaces and exploiting closed-form transport on trees. Existing tree-sliced constructions, however, are largely built around first-order Wasserstein geometry. While this choice yields efficient computation, it fixes the discrepancy to an $L^1$-type aggregation of subtree mass imbalances and provides limited control over the geometry used in downstream optimization. We propose Tree-Sliced Orlicz IPM (TS-Orlicz), a tree-sliced framework that replaces the tree-level $W_1$ discrepancy with an Orlicz integral probability metric. Building on the tractable formulation of Orlicz IPMs on trees, TS-Orlicz aggregates Orlicz-induced discrepancies over random tree systems while preserving the scalability of tree-sliced computation. By varying the underlying Orlicz function, the framework recovers $L^p$-type behavior and also supports non-polynomial, tail-sensitive geometries that emphasize large subtree discrepancies. We show that TS-Orlicz preserves key properties of tree-sliced constructions and admits efficient computation via closed-form special cases and one-dimensional scalar optimization. We further extend the framework to probability measures on hyperspheres. Experiments across Euclidean and spherical settings, including gradient flows, self-supervised learning, and diffusion-based generative modeling, show that Orlicz-induced tree-sliced discrepancies achieve competitive or improved performance over sliced and tree-sliced baselines while maintaining low computational cost.

We study $N$-armed stochastic dueling bandits under the Condorcet-winner assumption, where three widely adopted objectives are considered: best-arm identification (BAI), weak regret, and strong regret. We propose *Tree-Guided Identify-Then-Exploit (TG-ITE)*, the first unified framework to tackle all these objectives to our knowledge. Without requiring stronger assumptions, we propose a shared tree-guided identification approach to find a high-confidence incumbent within $O(N)$ comparisons. We further propose varied exploitation strategies to utilize this warm-start stage to optimize the specific objectives at hand. This methodology enables our approach to (1) achieve $O(N)$ sample complexity in BAI without commonly adopted stronger assumptions; (2) build the first winner-stays-style algorithm to achieve $O(N)$ weak regret; (3) enjoy the same $O(N \log T)$ guarantee as specialized strong-regret approaches; (4) realize the joint optimization of BAI and weak regret with $O(N)$ guarantees for both, eliminating the sub-optimal gap of $O(\log N)$ in the existing approach. Our results provide evidence that the trade-off between BAI and regret minimization is relatively benign in dueling bandits.

It is widely recognized that in many applications, strong predictive performance is not enough to warrant use of a learned model. Additionally, it is required to ascertain whether the model conforms to certain properties such as fairness, robustness or safety. Unfortunately, most learning approaches are not guaranteed to produce a model that adheres to these properties. Model repair addresses this through a post-hoc debugging loop. Approaches such as verification are used to check if the desired property holds for a model; if not they return a counterexample which is used to modify or repair the ML model. We propose a novel repair method for tree ensembles. Our approach is based on a MILP encoding where the objective is to modify the leaf values in the tree ensemble such that it fixes the counterexamples while at the same time preserves predictive performance. The use of constrained optimization over the model parameters is compelling as it is guaranteed to fix a given set of counterexamples. We implement and evaluate our method in two use-case scenarios, classification requiring fairness and action policies in MDPs requiring safety. Results show that our MILP repair of tree ensembles can be feasible computationally, and is often successful in improving the desired property while not degrading performance.

Whenever LLM training involves multiple outputs from the same input---agentic multi-turn trajectories, self-consistency reasoning, beam search distillation, or multi-rollout SFT/RL---the tokens form a tree-structured trajectory with shared prefixes. Existing pipelines linearize such data and treat each branch independently, causing substantial redundant computation that scales with the number of samples. We derive that averaging the loss over all branches is algebraically identical to a per-token weighted loss, reducing the problem to computing each token's log-probability exactly once. We propose DFS serialization of the tree, which visits every token exactly once, and adapt full-attention and SSM layers to ensure the resulting log-probabilities match independent per-branch computation exactly. For memory-constrained settings where the full tree exceeds GPU capacity, we propose Redundancy-Free Tree Partitioning, which achieves zero redundant computation with peak memory bounded by a single root-to-leaf path. Together, these contributions form Tree Training, achieving up to 6.2× end-to-end training speedup on dense and MoE models for both supervised fine-tuning and reinforcement learning.

Algorithms with predictions, or learning-augmented algorithms, has proved to be an extremely useful paradigm for combining machine learning with traditional algorithms. One of the textbook settings for this is searching a sorted array. Without a prediction classical binary search takes $O(\log n)$ queries, while with a prediction we can use "doubling binary search" to find the target key using $O(\log \eta)$ queries, where $\eta$ is the error of the prediction measured as the absolute value of the difference between the true location and the predicted location. Since an array is just a path graph, in this paper we ask whether similar bounds can be achieved for search on even slightly more general graphs: trees. We show first that the high-level answer is "no": there is no search algorithm that uses $O(\log \eta)$ queries, where now $\eta$ is the graph distance between the predicted location and the true location. However, as our main result, we show that such bounds can be achieved on trees which are "path-like" in that they have low pathwidth. In particular, we prove that there is a search algorithm which uses at most $O(k \log \eta)$ queries, where $k$ is the pathwidth of the tree. We also prove a lower bound showing that our algorithm has existentially optimal query complexity. Finally, we show experimentally, on real-life inputs, that our algorithm has query complexity which is notably better than the simple non-prediction based algorithm.

Large language models rely on positional representations for long context modeling, yet are typically trained on short sequences and evaluated at much longer lengths. Bridging this gap requires positional encodings remaining distinguishable at large distances while generalizing beyond the training length. In this paper, we identify a structural limitation of existing rotary-based positional encodings: all positional dimensions are controlled by a single global index, which couples training-time positional variation with long-range extrapolation. To address this, we propose Tree Rotary Positional Encoding (TPE), a structured multi-scale positional encoding designed for training from scratch that represents absolute positions through com positions of different components, avoiding single-index extrapolation. We further devise an Offset-based Positional Training (OPT) strategy to improve learning interactions across TPE components, enabling better generalization to longer con texts. We theoretically analyze that its multi-scale decomposition enables effective combinatorial position coverage. Experimental results show strong gains under extreme length extrapolation: with a 1.2B model trained from scratch on length 512, our TPE achieves a 64× extrapolation to 32K tokens, reducing perplexity from 4532.21 (RoPE) to 149.96, with comparable inference-time efficiency.

Large Language Model (LLM) agents increasingly excel at complex tasks, yet a persistent bottleneck emerges at the boundary of rule-based systems. Here, the core challenge is often not comprehending intent, but routing user intent through a prescribed, executable interface. This paper posits that this routing problem is best addressed not by scaling model reasoning alone, but by treating the interface itself—specifically, Domain-Specific Languages (DSLs) and their attached verifiers—as first-class boundary infrastructure. We argue that an effective DSL functions as a cognitive shortcut: by providing a high-abstraction, strongly constrained representation, it can compress the intent-to-action path, prune invalid actions before they are attempted, and mechanistically verify correctness via its harness. Our central contribution is to frame the deliberate selection, design, and evaluation of such language--harness pairings as an under-studied research variable that directly shapes an agent's effective action space, failure modes, and learning signals. We develop this position through a dual lens of lifecycle and domain analyses, and ground it with targeted case studies.