ICLR 2026 Papers

We propose ETGS, a method for reconstructing dynamic thermal scenes by embedding explicit thermodynamic modeling into 3D Gaussian Splatting. Each Gaussian is equipped with physically interpretable thermal parameters, and its thermaldynamics evolution is described by a first-order heat-transfer ODE with an analytical closed-form solution. This formulation avoids numerical integration, enables efficient rendering at arbitrary timestamps, and naturally handles irregular sampling and out-of-order observations. We also introduce the Rapid Heat Dynamics (RHD) dataset, which provides millisecond-aligned RGB–IR image pairs covering typical thermal processes such as cooling, warming, heating, and heat transfer. Experiments on RHD show that ETGS captures rapid thermal dynamics more accurately than existing static and dynamic baselines, while maintaining training and rendering efficiency close to that of static 3DGS. Code and dataset will be released.

Existing diffusion-based object removal and inpainting methods often fail to recover the fine structural and textural details of small objects. This is primarily due to the VAE encoder’s downsampling, which inevitably compresses small masked regions and causes significant detail loss, while the decoder’s upsampling alone cannot fully restore the lost fine details. However, the adverse effects of this fixed compression can be mitigated by enlarging the perspective of these regions. To this end, we propose ReFocusEraser, a two-stage framework for small object removal that combines camera-adaptive zoom-in inpainting with robust context- and shadow-aware repair. In Stage I, a camera-adaptive refocus mechanism magnifies masked regions, and a LoRA-tuned diffusion model ensures precise semantic alignment for accurate reconstruction. However, reintegrating these magnified inpainted regions into the original image introduces challenges due to VAE asymmetry, such as color shifts and seams. Stage II addresses these issues by fine-tuning an additional decoder to create a seam- and shadow-aware module that eliminates residual artifacts while preserving background consistency. Extensive experiments demonstrate that our proposed RefocusEraser achieves state-of-the-art performance, outperforming existing methods across benchmark datasets. Related code and data are available at https://github.com/ProAirVerse/ReFocusEraser.git.

Recent research on video Frame Interpolation (VFI) shows that a pretrained Video Diffusion Model (VDM) can solve many challenging scenarios, including large or complex motion. However, VDMs require tedious diffusion sampling, making the inference slow. One possible way to accelerate is to distill a multi-step model into a one-step model, but additional modules are often introduced during distillation, which significantly increase training overhead. Instead, we propose a Real-time Diffusion-based Video Frame Interpolation pipeline, \method. \method achieves efficient interpolation by disentangling this task into two subproblems: motion and appearance generation. Specifically, \method first calculates pixel movements across frames with the continuous motion fields, only utilizing a few sparse key frames. As a result, \method only forwards the diffusion model for these sparse key frames rather than for each intermediate frame, effectively reducing one-step training cost. In the second appearance estimation step, \method then only needs to create intermediate frames by warping input frames with sampled optical flows from the estimated continuous motion field in the first step. Because our diffusion model creates motions only, it can work at a fixed and relatively small resolution, leading to superior training and inference efficiency. Extensive experiments show that our \method generates comparable or superior interpolation quality compared with existing multi-step solutions. It also offers outstanding inference efficiency, interpolating 17FPS at $1024\times 576$ resolution, achieving \textbf{50$\times$ acceleration} than the fastest diffusion-based generation by Wan.

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently disrupt spatial layouts and temporal continuity by disregarding positional relationships. In this work, we propose a novel encoding operator dubbed as **P**ositional **P**reservation **E**mbedding (**PPE**), which has the main hallmark of preservation of spatiotemporal structure during visual token compression. PPE explicitly introduces the disentangled encoding of 3D positions in the token dimension, enabling each compressed token to encapsulate different positions from multiple original tokens. Furthermore, we show that PPE can effectively support cascade clustering --- a progressive token compression strategy that leads to better performance retention. PPE is a parameter-free and generic operator that can be seamlessly integrated into existing token merging methods without any adjustments. Applied to state-of-the-art token merging framework, PPE achieves consistent improvements of 2\%~5\% across multiple vision-language benchmarks, including MMBench (general vision understanding), TextVQA (layout understanding) and VideoMME (temporal understanding). These results demonstrate that preserving positional cues is critical for efficient and effective MLLM reasoning. Our code is available at https://github.com/MouxiaoHuang/PPE

Latent Diffusion Models (LDMs) have recently shown great potential for image restoration owing to their powerful generative priors. However, directly applying them to ultra-high-definition image restoration (UHD-IR) often results in severe global inconsistencies and loss of fine-grained details, primarily caused by patch-based inference and the information bottleneck of the VAE. To overcome these issues, we present FreeAdapt, a plug-and-play framework that unleashes the capability of diffusion priors for UHD-IR. The core of FreeAdapt is a training-free Frequency Feature Synergistic Guidance (FFSG) mechanism, which introduces guidance at each denoising step during inference time. It consists of two modules: 1) Frequency Guidance (FreqG) selectively fuses phase information from a reference image in the frequency domain to enforce structural consistency across the entire image; 2) Feature Guidance (FeatG) injects global contextual information into the self-attention layers of the U-Net, effectively suppressing unrealistic textures in smooth regions and preserving local detail fidelity. In addition, FreeAdapt includes an optional VAE fine-tuning module, where skip connection further enhances the reconstruction of fine-grained textures. Extensive experiments demonstrate that our method achieves superior quantitative performance and visual quality compared to state-of-the-art UHD-IR approaches, and consistently delivers strong gains across multiple LDM-based backbones.

Recent advances in Multimodal Large Language Models (MLLMs) have driven rapid progress in Vision–Language–Action (VLA) models for robotic manipulation. Although effective in many scenarios, current approaches largely rely on explicit instructions, whereas in real-world interactions, humans rarely issue instructions directly. Effective collaboration requires robots to infer user intentions proactively. In this work, we introduce *cross-modal contextual instructions, a new setting where intent is derived from spoken dialogue, environmental sounds, and visual cues rather than explicit commands.* To address this new setting, we present **RoboOmni**, a *Perceiver-Thinker-Talker-Executor* framework based on end-to-end omni-modal LLMs that unifies intention recognition, interaction confirmation, and action execution. RoboOmni fuses auditory and visual signals spatiotemporally for robust intention recognition, while supporting direct speech interaction. To address the absence of training data for proactive intention recognition in robotic manipulation, we build **OmniAction**, comprising 140k episodes, 5k+ speakers, 2.4k event sounds, 640 backgrounds, and six contextual instruction types. Experiments in simulation and real-world settings show that RoboOmni surpasses text- and ASR-based baselines in success rate, inference speed, intention recognition, and proactive assistance. All datasets, code, and real-world demonstration videos will be released publicly.

Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction, point cloud reconstruction, and point tracking—all without post-processing. Training a geometry transformer for dynamic scenes from scratch, however, demands large-scale dynamic datasets and substantial computational resources, which are often impractical. To overcome this, we propose an efficient fine-tuning strategy that allows PAGE-4D to generalize to dynamic scenarios using only limited dynamic data and compute. In particular, we design a dynamics-aware aggregator that disentangles dynamic from static content for downstream scene understanding tasks: it first predicts a dynamics-aware mask, which then guides a dynamics-aware global attention mechanism. Extensive experiments show that PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction. The source code and pretrained model weights are provided in the supplementary material.

Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy efficiency and biological realism. Most existing SNNs are based on neural dynamics such as the (leaky) integrate-and-fire (IF/LIF) models, which are described by \emph{first-order} ordinary differential equations (ODEs) with Markovian characteristics. This means the potential state at any time depends solely on its immediate past value, potentially limiting network expressiveness. Empirical studies of real neurons, however, reveal long-range correlations and fractal dendritic structures, suggesting non-Markovian behavior better modeled by \emph{fractional-order} ODEs. Motivated by this, we propose a \emph{fractional-order} spiking neural network (\emph{f}-SNN) framework that strictly generalizes integer-order SNNs and captures long-term dependencies in membrane potential and spike trains via fractional dynamics, enabling richer temporal patterns. We also release an open-source toolbox to support the \emph{f}-SNN framework, applicable to diverse architectures and real-world tasks. Experimentally, fractional adaptations of established SNNs into the \emph{f}-SNN framework achieve superior accuracy, comparable energy efficiency, and improved robustness to noise, underscoring the promise of \emph{f}-SNNs as an effective extension of traditional SNNs.

Indirect editing methods for 3D Gaussian Splatting (3DGS) have recently witnessed significant advancements. These approaches operate by first applying edits in the rendered 2D space and subsequently projecting the modifications back into 3D. *However, this paradigm inevitably introduces cross-view inconsistencies and constrains both the flexibility and efficiency of the editing process*. To address these challenges, we present **VF-Editor**, which enables native editing of Gaussian primitives by predicting attribute variations in a feedforward manner. To accurately and efficiently estimate these variations, we design a novel variation predictor distilled from 2D editing knowledge. The predictor encodes the input to generate a variation field and employs two learnable, parallel decoding functions to iteratively infer attribute changes for each 3D Gaussian. Thanks to its unified design, VF-Editor can seamlessly distill editing knowledge from diverse 2D editors and strategies into a single predictor, allowing for flexible and effective knowledge transfer into the 3D domain. Extensive experiments on both public and private datasets reveal the inherent limitations of indirect editing pipelines and validate the effectiveness and flexibility of our approach.

Reconstructing dynamic 3D scenes with photorealistic detail and temporal coherence remains a significant challenge. Existing Gaussian splatting approaches modeling scenes rely on per-frame optimization, causing them to overfit to instantaneous states rather than learning true motion dynamics. To address this, we present Mango-GS, a multi-frame, node-guided framework for high-fidelity 4D reconstruction. Our approach leverages a temporal Transformer to learn complex motion dependencies across a window of frames, ensuring the generation of plausible trajectories. For efficiency, this temporal modeling is confined to a sparse set of control nodes. These nodes are uniquely designed with decoupled position and latent codes, which provide a stable semantic anchor for motion influence and prevents correspondence errors for large movements. Our framework is trained end-to-end, enhanced by a input masking strategy and two multi-frame loss to ensure robustness. Extensive experiments demonstrate that Mango-GS achieves state-of-the-art quality and fast rendering speed, enabling high-fidelity reconstruction and real-time rendering of dynamic scenes.

In this paper, built upon TAPTRv2, we present TAPTRv3. TAPTRv3 improves TAPTRv2 by addressing its shortage in querying high quality features from long videos, where the target tracking points normally undergo increasing variation over time. In TAPTRv3, we propose to utilize both spatial and temporal context to bring better feature querying along the spatial and temporal dimensions for more robust tracking in long videos. For better spatial feature querying, we identify that off-the-shelf attention mechanisms struggle with point-level tasks and present Context-aware Cross-Attention (CCA). CCA introduces spatial context into the attention mechanism to enhance the quality of attention scores when querying image features. For better temporal feature querying, we introduce Visibility-aware Long-Temporal Attention (VLTA), which conducts temporal attention over all past frames while considering their corresponding visibilities. This effectively addresses the feature drifting problem in TAPTRv2 caused by its RNN-like long-term modeling. TAPTRv3 surpasses TAPTRv2 by a large margin on most of the challenging datasets and obtains state-of-the-art performance. Even when compared with methods trained on large-scale extra internal data, TAPTRv3 still demonstrates superiority.

This paper tackles \textbf{open-ended deep research (OEDR)}, a complex challenge where AI agents must synthesize vast web-scale information into insightful reports. Current approaches are plagued by dual-fold limitations: static research pipelines that decouple planning from evidence acquisition and monolithic generation paradigms that include redundant, irrelevant evidence, suffering from hallucination issues and low citation accuracy. To address these challenges, we introduce \textbf{WebWeaver}, a novel dual-agent framework that emulates the human research process. The planner operates in a dynamic cycle, iteratively interleaving evidence acquisition with outline optimization to produce a comprehensive, citation-grounded outline linking to a memory bank of evidence. The writer then executes a hierarchical retrieval and writing process, composing the report section by section. By performing targeted retrieval of only the necessary evidence from the memory bank via citations for each part, it effectively mitigates long-context issues and citation hallucinations. Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym. These results validate our human-centric, iterative methodology, demonstrating that adaptive planning and focused synthesis are crucial for producing comprehensive, trusted, and well-structured reports.

Radiance of real-world scenes typically spans a much wider dynamic range than what standard cameras can capture, often leading to saturated highlights or underexposed shadows. While conventional HDR methods merge alternatively exposed frames, most approaches remain constrained to the 2D image plane, failing to model geometry and motion consistently. To address these limitations, we present HDR-NSFF, a novel framework for reconstructing dynamic HDR radiance fields from alternatively exposed monocular videos. Our method explicitly models 3D scene flow, HDR radiance, and tone mapping in a unified end-to-end pipeline. We further enhance robustness by (i) extending semantic-based optical flow with DINO features to achieve exposure-invariant motion estimation, and (ii) incorporating a generative prior as a regularizer to compensate for sparse-view and saturation-induced information loss. To enable systematic evaluation, we construct a real-world GoPro dataset with synchronized multi-exposure captures. Experiments demonstrate that HDR-NSFF achieves state-of-the-art performance in novel view and time synthesis, recovering fine radiance details and coherent dynamics even under challenging exposure variations and large motions.

Developing biologically plausible learning algorithms that can achieve performance comparable to error backpropagation remains a longstanding challenge. Existing approaches often compromise biological plausibility by entirely avoiding the use of spikes for error propagation or relying on both positive and negative learning signals, while the question of how spikes can represent negative values remains unresolved. To address these limitations, we introduce Bidirectional Spike-based Distillation (BSD), a novel learning algorithm that jointly trains a feedforward and a backward spiking network. We formulate learning as a transformation between two spiking representations (i.e., stimulus encoding and concept encoding) so that the feedforward network implements perception and decision-making by mapping stimuli to actions, while the backward network supports memory recall by reconstructing stimuli from concept representations. Extensive experiments on diverse benchmarks, including image recognition, image generation, and sequential regression, show that BSD achieves performance comparable to networks trained with classical error backpropagation. These findings represent a significant step toward biologically grounded, spike-driven learning in neural networks.

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalizes weakly to new scenarios. Agentic systems offer a promising alternative by decomposing work across specialized modules, yet most remain training-free or rely on offline training decoupled from the live dynamics of multi-turn interaction. We introduce AgentFlow, a trainable, *in-the-flow* agentic framework that coordinates four modules (planner, executor, verifier, generator) through an evolving memory and directly optimizes its planner inside the multi-turn loop. To train on-policy in live environments, we propose *Flow-based Group Refined Policy Optimization* (Flow-GRPO), which tackles long-horizon, sparse-reward credit assignment by converting multi-turn optimization into a sequence of tractable single-turn policy updates. It broadcasts a single, verifiable trajectory-level outcome to every turn to align local planner decisions with global success and stabilizes learning with group-normalized advantages. Across ten benchmarks, AgentFlow with a 7B-scale backbone outperforms top-performing baselines with average accuracy gains of 14.9% on search, 14.0% on agentic, 14.5% on mathematical, and 4.1% on scientific tasks, even surpassing larger proprietary models like GPT-4o. Further analyses confirm the benefits of in-the-flow optimization, showing improved planning, enhanced tool-calling reliability, and positive scaling with model size and reasoning turns. Codebase is available at https://anonymous.4open.science/r/agentflow.

Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert models into a single, more capable model, reducing storage and serving costs while supporting decentralized development. Despite its potential, previous studies have primarily focused on merging visual classification models or Large Language Models (LLMs) for code and math tasks. Recently, Multimodal LLMs (MLLMs) that extend LLMs through large-scale multimodal training have gained traction. However, no benchmark exists for model merging research that clearly divides the tasks of MLLM training and evaluation. In this paper, $(i)$ we introduce a model merging benchmark for MLLMs, which includes multiple tasks such as VQA, Geometry, Chart, OCR, and Grounding, studying both LoRA and full fine-tuning models. Moreover, we explore how model merging can combine different modalities (e.g., vision-language, audio-language, and video-language models), moving toward the Omni-language model. $(ii)$ We implement 10 model merging algorithms on the benchmark. Furthermore, we propose a novel method that removes noise from task vectors and robustly optimizes the merged vector based on a loss defined over task vector interactions, achieving an average performance gain of 2.48\%. $(iii)$ We find that model merging offers a promising way for building improved MLLMs without requiring training data. Our results also demonstrate that the complementarity among multiple modalities outperforms individual modalities.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spatiotemporal interactions through hierarchical temporal gridding, and Norm-based Spatial Pooling (NSP), which preserves high-information visual regions by leveraging the correlation between token norms and semantic richness. Extensive experiments on various benchmarks demonstrate that ST-GridPool consistently enhances performance of Video LLMs without requiring costly retraining. Our method offers an efficient and plug-and-play solution for improving visual token representations. Our code is available in [https://anonymous.4open.science/r/ST-GridPool-85BE](https://anonymous.4open.science/r/ST-GridPool-85BE).

Recent 4D Gaussian Splatting (4DGS) methods often fail under fast motion with large inter-frame displacements, where Gaussian attributes are poorly learned during training, and fast-moving objects are often lost from the reconstruction. In this work, we introduce Spatiotemporal Position Implicit Network for 4DGS, coined SPIN-4DGS, which learns Gaussian attributes from explicitly collected spatiotemporal positions rather than modeling temporal displacements, thereby enabling more faithful splatting under fast motions with large inter-frame displacements. To avoid the heavy memory overhead of explicitly optimizing attributes across all spatiotemporal positions, we instead predict them with a lightweight feed-forward network trained under a rasterization-based reconstruction loss. Consequently, SPIN-4DGS learns shared representations across Gaussians, effectively capturing spatiotemporal consistency and enabling stable high-quality Gaussian splatting even under challenging motions. Across extensive experiments, SPIN-4DGS consistently achieves higher fidelity under large displacements, with clear improvements in PSNR and SSIM on challenging sports scenes from the CMU Panoptic dataset. For example, SPIN-4DGS notably outperforms the strongest baseline, D3DGS, by achieving +1.83 higher PSNR on the Basketball scene.

Large Language Model (LLM)-based agents have emerged as a transformative approach for open-ended problem solving, with information seeking (IS) being a core capability that enables autonomous reasoning and decision-making. While prior research has largely focused on improving retrieval depth, we observe that current IS agents often suffer from \textit{low search efficiency}, which in turn constrains overall performance. A key factor underlying this inefficiency is the sparsity of target entities in training tasks, which limits opportunities for agents to learn and generalize efficient search behaviors. To address these challenges, we propose WebLeaper, a framework for constructing high-coverage IS tasks and generating efficient solution trajectories. We formulate IS as a tree-structured reasoning problem, enabling a substantially larger set of target entities to be embedded within a constrained context. Leveraging curated Wikipedia tables, we propose three variants for synthesizing IS tasks—Basic, Union, and Reverse-Union—to systematically increase both IS efficiency and effectiveness. Finally, we curate training trajectories by retaining only those that are simultaneously accurate and efficient, ensuring that the model is optimized for both correctness and search performance. Extensive experiments conducted on five IS benchmarks—BrowserComp, GAIA, Seal-0, WideSearch, and xbench-DeepSearch—demonstrate that our method consistently achieves improvements in both effectiveness and efficiency over strong baselines.