NeurIPS 2026 论文列表

Understanding 4D scenes is a core challenge in visual intelligence, requiring models to jointly capture scene geometry, appearance, and dynamics from partial observations. Existing approaches, however, are subdivided into feedforward models that are used for direct geometric prediction and generative models for visual synthesis. We propose a unified generative-predictive framework for 4D scene understanding that jointly models RGB video and geometric representations such as depth and camera pose with a single joint generative model. Our generative formulation enables us to learn from diverse, heterogeneous datasets with different subsets of geometric and visual annotations, and enables us to condition on arbitrary subsets of inputs, allowing a single model to perform cross-modal generation, geometric prediction, and future scene inference from partial observations. In addition, our generative approach enables test-time search over multiple candidate scene completions, improving geometric prediction from sparse observations. Overall, we illustrate the efficacy of our generative-predictive framework on a suite of generation and prediction tasks.

Despite rapid progress in synthetic image detection, detectors that perform well on known generators often become brittle when the source model, post-processing pipeline, or scene composition changes. A key reason is that standard binary supervision teaches models to separate training distributions rather than to identify authenticity-relevant evidence: low-level artifacts become shortcuts, while higher-level semantic implausibilities remain weakly grounded. To address this limitation, we propose **UniFPL**, a unified forensics preference learning framework that converts multimodal large language model (MLLM) forensic knowledge into image-specific preference supervision. UniFPL constructs forensic preference data from both controlled artifact synthesis and observed artifact harvesting, then learns from list-level evidence rankings that encode which visual-textual cues are more diagnostic of synthetic manipulation. On top of a CLIP-based discriminative detector, UniFPL jointly optimizes authenticity classification, artifacts-aware preference alignment, and semantic structure regularization, allowing the model to inherit contextual forensic reasoning while retaining the stable and efficient inference of a discriminative encoder. Across eleven curated and in-the-wild benchmarks, UniFPL achieves an average balanced accuracy of 93.4\% and improves the worst-case accuracy from 81.4\% to 86.1\% over the strongest baseline, demonstrating stronger cross-generator generalization and robustness to real-world image degradations.

Speculative decoding accelerates Large Language Models via draft-then-verify, where verification can be framed as an Optimal Transport (OT) problem. Existing approaches typically handle multi-draft and multi-step aspects in isolation, applying either flat OT to single-step drafts or per-token rejection sampling to tree-structured candidates. This separation leaves the joint regime (where multi-step dependencies meet multi-draft branching) poorly optimized, as local verification rules fail to exploit the coupling between horizontal and vertical dimensions of candidate trees. In this paper, we propose a unified perspective that casts tree-based verification as a conditional OT problem. Our key insight is that vertical dependencies can be abstracted through prefix acceptance probabilities, which act as dynamic scaling factors to actively guide horizontal draft selection. Based on this principle, we introduce UniVer, a verification algorithm that jointly optimizes across tree levels by composing local optimal transport plans under prefix constraints. We prove that UniVer remains lossless and achieves the optimal acceptance rate under the proposed conditional framework. Extensive experiments across different tasks and models demonstrate that UniVer improves acceptance length by 4.2\% to 8.5\% over standard recursive rejection sampling without replacement, while maintaining exact distributional alignment with the target model.

Multimodal large language models are increasingly expected to perform \emph{thinking with images}, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved design limits efficiency and keeps reasoning fragmented across separate text and vision channels. We propose **UniVLR**, a unified visual latent reasoning framework that treats textual reasoning and auxiliary visual evidence as a shared visual workspace. Instead of preserving text CoT as an independent inference-time path, UniVLR renders reasoning traces together with auxiliary images and learns to compress this unified representation into compact visual latent tokens. At inference time, the model reasons only through visual latents and directly decodes the final answer, avoiding both external tool calls and verbose text reasoning. Experiments on real-world perception and visual reasoning tasks show that UniVLR outperforms prior visual latent reasoning methods while using substantially fewer generated reasoning tokens, suggesting a more unified and efficient paradigm for visual thinking in MLLMs. Our code is available at: https://anonymous.4open.science/r/UniVLR-1B0C/.

In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across diverse camera systems, such as large-field-of-view fisheye lenses. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, 2D semantic embeddings and 3D spatial features are jointly encoded and decoded by UniK3D to support Gaussian construction, while a ray-based universal representation organizes Gaussian primitives along rays and radial distances. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems, including pinhole, fisheye and panoramic cameras, across various scenes. The benchmark is further stratified by field of view, spanning narrow perspective, wide-FoV, fisheye, and full panoramic settings. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. Our models, training code, and dataset will be publicly available.

We identify, for the first time, a new model modification attack—the cross-task model repurposing attack—that can render fingerprints generated by existing model fingerprinting approaches inapplicable. To address this challenge, we propose UniReFP—a novel unified model fingerprinting framework applicable to diverse vision models across different tasks—that utilizes ownership evidence in a shared class-level semantic space rather than original task-specific output space, enabling effective ownership verification when a protected model is repurposed across tasks with heterogeneous output formats. Specifically, UniReFP constructs a surrogate classifier by repurposing the protected model, enabling fingerprints to be generated independently of the original task-dependent output space of the protected model. Moreover, it optimizes grouped fingerprints to encode ownership evidence: fingerprints within the same group are encouraged to induce consistent semantic responses and intermediate representations on the surrogate classifier, while producing dispersed responses on independently trained reference classifiers. During verification, UniReFP uses a task-aware semantic projection mechanism to map heterogeneous suspect-model outputs into unified semantic-presence vectors, and determines ownership by measuring inner-group consistency. Extensive experimental results validate the effectiveness of UniReFP, consistently showing superior performance under cross-task repurposing attacks, commonly studied model modification attacks, and even their combinations.

List-wise reranking arranges a request-specific pool of candidate items into an ordered slate that maximizes user satisfaction. Existing generative rerankers fall into two paradigms: Autoregressive (AR) rerankers construct the slate left to right and capture inter-item dependencies in the exposure list, but they suffer from error propagation because early mistakes affect subsequent slots. Non-autoregressive (NAR) rerankers predict all slots in parallel and avoid error propagation, but they weaken inter-item interaction modeling under a slot independence assumption. This raises a central question: is there a unified architecture that combines the strengths of both paradigms and delivers stronger reranking performance? We answer this question with UniRank, a unified list-wise reranking framework whose inference time variants recover AR and NAR rerankers as special cases. UniRank integrates bidirectional slate modeling into an iterative denoising process and fills the most confident slot at each step. To instantiate this framework for reranking, we introduce the Task Grounded Diffusion Interface (TGD), which performs denoising at the item level and restricts prediction to the request-specific candidate pool. TGD aggregates each item's semantic tokens into a single item embedding and scores each slot directly against the candidate pool. Experiments on Amazon Books, MovieLens-1M, and an industrial short video dataset show that UniRank consistently outperforms state-of-the-art baselines. Our code is available online.

Vision-language perception has achieved impressive progress in aligning natural language with visual observations, yet grounding high-level semantics into part-level physical interaction remains challenging. To address this gap, we propose UniRAP, a unified model for inferring part-level physical affordances and mapping language instructions to actionable geometric representations. UniRAP formulates this problem as a conditional multimodal generation task, integrating visual inputs, textual instructions, and optional prompts into a shared spatiotemporal representation space through a unified interface token mechanism. To predict executable contact geometry, we introduce a Unified Affordance Decoder (UAD), which jointly performs object detection, part-level affordance segmentation, and 4-DoF interaction pose estimation by leveraging intermediate segmentation features. In addition, we propose a curriculum-based transfer training strategy that progressively adapts the model from general visual parsing to interaction-aware perception, improving data efficiency under limited textual annotations. Experiments show that UniRAP achieves state-of-the-art performance on referring expression segmentation, affordance grounding, and interaction pose estimation, while maintaining strong spatiotemporal consistency in dynamic video scenarios. These results demonstrate the effectiveness of UniRAP as a unified perception framework for language-guided physical manipulation. All data and code will be made publicly available.

As large language models (LLMs) continue to advance rapidly, they are becoming increasingly capable while simultaneously demanding ever-longer context lengths. To improve the inference efficiency of long-context processing, several novel low-complexity hybrid architectures have recently been proposed, effectively alleviating the computational burden of long-context inference. However, existing research on long-context prefill acceleration remains predominantly focused on sparse attention mechanisms, which achieve their maximum speedup only on full-attention models. When transferred to emerging architectures — such as linear/full attention hybrids or sliding window/full attention hybrids — these prefill acceleration approaches suffer significant performance degradation. Furthermore, such methods are generally incompatible with continuous batching, making them difficult to integrate into modern inference engines such as vLLM. To this end, we propose UniPrefill, a prefill acceleration framework applicable to virtually any model architecture, which directly accelerates the model's computation at the token level. We further implement UniPrefill as a continuous batching operator and extend vLLM's scheduling strategy to natively support prefill-decode co-processing for UniPrefill, enabling its seamless integration into vLLM. UniPrefill achieves up to 2.1x speedup in Time-To-First-Token (TTFT), with the acceleration becoming increasingly pronounced as the number of concurrent requests grows.

Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture. However, it remains underexplored how to effectively coordinate these two capabilities for more effective and efficient reasoning. Existing coordination approaches either perform coupling during training, without explicit inference-time coordination, or impose a fixed coordination pattern for all inputs. In this work, we show that multimodal tasks exhibit substantial coordination-path diversity: different inputs favor different coordination paths. This suggests that exploiting such diversity is key to improving performance. We propose UniPath, a framework for adaptively modeling and exploiting coordination-path diversity. Instead of enforcing a single coordination pattern, we represent task solving as the selection and execution of a path, ranging from direct answering to textual inference, visual-thought construction, and hypothesis-based exploration. We construct role-aligned trajectories to train a path-conditioned executor and introduce a lightweight planner mechanism to enable input-dependent path selection. Experiments show that leveraging coordination-path diversity improves performance over fixed coordination strategies while providing interpretable intermediate behaviors. The code is available at: https://anonymous.4open.science/r/UniPath.

In this paper, we propose UniGS, a unified map representation and differentiable framework for high-fidelity multimodal 3D reconstruction based on 3D Gaussian Splatting. Our framework integrates a CUDA-accelerated rasterization pipeline capable of rendering photo-realistic RGB images, geometrically accurate depth maps, consistent surface normals, and semantic logits simultaneously. We redesign the rasterization to render depth via differentiable ray-ellipsoid intersection rather than using Gaussian centers, enabling effective optimization of rotation and scale attribute through closed-form analytic depth gradients. Furthermore, we derive the analytic gradient formulation for surface normal rendering, ensuring geometric consistency among the reconstructed 3D scenes. To improve computational and storage efficiency, we introduce a learnable attribute that enables differentiable pruning of Gaussians with minimal contribution during training. Quantitative and qualitative experiments demonstrate the state-of-the-art reconstruction accuracy across several datasets, validating the efficacy and robust optimization stability of our geometry-aware paradigm.

Affordance segmentation in 3D scenes requires an agent to ground implicit natural-language instructions into precise masks of fine-grained interactive elements. Existing training-free methods typically rely on fragmented pipelines, which introduce visual blindness during task parsing and limit accuracy through single-scale spatial and temporal processing. We present UniFunc3D, a unified and training-free framework that treats the multimodal large language model as an active observer. By consolidating semantic, temporal, and spatial reasoning into a single forward pass, UniFunc3D performs joint reasoning to ground task decomposition in direct visual evidence. Our approach introduces active spatial-temporal grounding with a coarse-to-fine strategy. This allows the model to select correct video frames adaptively and focus on high-detail interactive parts while preserving the global context necessary for disambiguation. On SceneFun3D, our UniFunc3D achieves state-of-the-art performance, surpassing prior training-free methods by a large margin with a relative 59.9\% mIoU improvement, and even outperforming training-based methods without any task-specific training. Code will be released.

Flexible molecular docking is crucial for drug discovery; however, existing flow-matching generative models often produce physically invalid conformations (e.g., steric clashes, distorted bond geometry). Our analysis suggests that a primary contributor to this challenge lies at the modeling level: when the flow is parameterized by standard equivariant networks, an intrinsic approximation floor can emerge, potentially hindering the learned velocity field from reaching its optimal convergence bound, particularly for highly flexible molecules. We present UniFlowDock, which addresses this by introducing strictly Complete Equivariant Velocity Fields, thereby eliminating the dimensional incompleteness of standard architectures. This theoretical completeness is further bolstered by Fragment-Adaptive Optimal Coupling, a method that structurally linearizes transport trajectories and decomposes the generation process into physics-aware subproblems. Experiments on PDBBind and PoseBusters demonstrate UniFlowDock achieves state-of-the-art accuracy and physical validity, showing consistent gains in highly flexible docking scenarios where target distributions exhibit higher transport complexity.

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual conditioning: semantic ViT features are processed by the VLM for instruction understanding, whereas appearance-rich VAE features are injected later into the diffusion backbone. Despite its intuitive design, this separation makes it difficult for the model to associate each semantically grounded subject with visual details from the correct reference image. As a result, the model may recognize which subject is being referred to, but fail to preserve its identity and fine-grained appearance, leading to attribute leakage and cross-reference confusion in complex multi-reference settings. To address this issue, we propose UniCustom, a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding. This early fusion exposes the VLM to both semantic cues and appearance-rich details, enabling its hidden states to jointly encode the referred subject and corresponding visual appearance with only a lightweight linear fusion layer. To learn such unified representations, we adopt a two-stage training strategy: reconstruction-oriented pretraining that preserves reference-specific appearance details in the fused hidden states, followed by supervised finetuning on single- and multi-reference generation tasks. We further introduce a slot-wise binding regularization that encourages each image slot to preserve low-level details of its corresponding reference, thereby reducing cross-reference entanglement. Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity over strong baselines. Our code, checkpoints, and the training dataset will be released soon.

We introduce $\textbf{UniCon3R}$, a unified feed-forward framework for online human-scene 4D reconstruction from monocular video. Current feed-forward human-scene reconstruction methods suffer from artifacts, where bodies float above the ground or penetrate parts of the scene. A key reason is the lack of effective interaction modelling between the human and the environment. Our goal is to exploit contact between the human and the scene during inference to actively improve the human mesh reconstruction. To that end, we explicitly model interaction by inferring 4D contact from the human pose and scene geometry and use the contact as a corrective cue for generating the pose. This enables UniCon3R to jointly recover scene geometry and spatially aligned 4D humans within the scene. Experiments on standard human-centric video benchmarks show that UniCon3R outperforms state-of-the-art baselines on physical plausibility and global human motion estimation while preserving fast, feed-forward inference speeds. The results validate our central claim: contact serves as a powerful internal prior, thus establishing a new paradigm for physically grounded joint human-scene reconstruction. Source code and models will be released upon acceptance.

The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniClawBench, the first capability-driven benchmark designed to evaluate proactive agents in dynamic, real-world settings. UniClawBench is built around five foundational model capabilities: Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, and Cross-Platform Coordination. Based on these capabilities, we design 400 bilingual real-world tasks. Unlike previous benchmarks that rely on static, pre-recorded answers, our benchmark evaluates agents in live Docker containers using fine-grained, step-by-step completion checkpoints. Furthermore, we design a closed-loop evaluation strategy comprising an executor agent, a hidden supervisor agent, and a user agent to simulate realistic multi-turn human feedback without leaking grading criteria. To disentangle base model capabilities from framework-level design choices, we evaluate state-of-the-art models under multiple agent frameworks. Through comprehensive comparisons across both models and frameworks, we show how base model capabilities and agent framework designs jointly shape performance in real-world environments.

Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to fully capture the potential synergy between comprehension and creation. In this work, we propose Sync-R1, an end-to-end reinforcement learning framework that jointly optimizes personalized understanding and generation within a single, explicit reasoning loop. Through this unified feedback process, Sync-R1 enables personalized comprehension to guide content creation, while the resulting generation quality reciprocally refines understanding within an integrated reward landscape. To efficiently orchestrate this dual-task synergy, we introduce Sync-GRPO, a reinforcement learning method utilizing an ensemble reward system. Furthermore, we propose Dynamic Group Scaling (DGS), which adaptively filters low-potential trajectories to reduce gradient variance and accelerate convergence. To better reflect real-world complexity, we introduce UnifyBench++, featuring denser textual descriptions and richer user contexts. Experimental results demonstrate that Sync-R1 achieves state-of-the-art performance, showcasing superior cross-task reasoning and robust personalization without requiring complex cold-start procedures.

Articulated 3D objects are essential for interactive environments in embodied AI, robotics, and virtual reality, but reconstructing their structure and motion from sparse observations remains challenging. Existing approaches remain largely constrained by lack of supervised data or lack priors needed to reliably recover articulation, hidden geometry, and internal object structure. We present the first hierarchical agentic approach for articulated 3D object reconstruction from text or image inputs, combining hierarchical, debate-based reasoning with a video generative prior for articulation modeling. High-level agents reason about object semantics and motion using knowledge from vision-language and video models, while low-level agents estimate articulation parameters and interaction points; together, they engage in structured debate to resolve ambiguities in structure and motion. To enable reliable generation, including interior object structures, from only text or image inputs, we introduce a video generative model prior that not only synthesizes plausible object motions, but also expose occluded interiors and geometry that cannot be inferred from a single static view. By combining agentic reasoning with a video generative prior, our approach jointly infers articulation and reconstructs complete 3D articulated objects, producing high-fidelity geometry, internal structure, and motion-consistent states beyond directly observed surfaces.

Chain-of-Thought (CoT) reasoning substantially improves Large Language Models (LLMs), yet its out-of-distribution (OOD) generalization mechanism remains theoretically underexplored. We study CoT as compositional OOD generalization: the target task lacks complete reasoning trajectories or direct input-output pairs, while training provides only in-distribution (ID) atomic step data. We show that CoT generalizes by repeatedly applying a shared single-step predictor to compose reusable ID transitions. Theoretically, the OOD task risk is controlled by the sum of ID subtask risks, with an error-propagation coefficient independent of reasoning depth/steps $T$. A Rademacher-complexity analysis further gives a generalization gap of $\mathcal{O}(\sqrt{T/n})$, rather than linear in $T$, due to predictor sharing, where $n$ denotes training samples per subtask. For autoregressive Next-Token Prediction, we derive an explicit bound $\mathcal{O}\big(k\big(\sqrt{{T}/{mn}}+\sqrt{{T}/{n}}+{T}/{m}\big)\big)$, where $m$ and $k$ denote context length and output token number per step. Experiments on Atom-Task and GSM8K support the theory, showing that CoT enables short-to-long and compositional generalization, while explicit state tracking is crucial.