arXiv subjects

Yang You

Publications and source records attributed to Yang You.

At least 55 records · Page 3Linked to original sources

arXiv2026

PhysMem: Scaling Test-Time Memory for Embodied Physical Reasoning

Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction and stability in general terms; however, they often cannot predict how a specific ball will roll on a particular surface or which stone will provide a stable foundation without direct experience. We present PhysMem, a memory framework that enables VLM robot planners to learn physical principles from interaction at test time, without updating model parameters. The system records experiences, generates candidate hypotheses, and verifies them through targeted interaction before promoting validated knowledge to guide future decisions. A central design choice is verification before application: the system tests hypotheses against new observations rather than applying retrieved experience directly, reducing rigid reliance on prior experience when physical conditions change. We evaluate PhysMem on three real-world manipulation tasks and simulation benchmarks across four VLM backbones. On a controlled brick insertion task, principled abstraction achieves 76% success compared to 23% for direct experience retrieval, and real-world experiments show consistent improvement over 30-minute deployment sessions.

cs.RO↗

arXiv2026

TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation

Unified audio-visual generation is rapidly gaining industrial and creative relevance, enabling applications in virtual production and interactive media. However, when moving from general audio-video synthesis to music-dance co-generation, the task becomes substantially harder: musical rhythm, phrasing, and accents must drive choreographic motion at fine temporal resolution, and such rhythmic coupling is not captured by unimodal metrics or generic audiovisual consistency scores used in current evaluation practice. We introduce TMD-Bench, a benchmark for text-driven music-dance co-generation that assesses systems across unimodal generation quality, instruction adherence, and cross-modal rhythmic alignment. The benchmark integrates computable physical metrics with perceptual multimodal judgments, and is supported by a curated rhythm-aligned music-dance dataset and a fine-grained Music Captioner for structured music semantics. TMD-Bench further reveals that (i) modern commercial audio-visual models, such as Veo 3 and Sora 2, produce high-quality music and video, while rhythmic coupling remains less consistently optimized and leaves room for improvement, and (ii) our unified baseline RhyJAM trained on rhythm-aligned data achieves competitive beat-level synchronization while maintaining competitive unimodal fidelity. This presents prospects for building next-generation music-dance models that explicitly optimize rhythmic and kinetic coherence.

cs.SD↗

arXiv2026

DOT-Sim: Differentiable Optical Tactile Simulation with Precise Real-to-Sim Physical Calibration

Simulating optical tactile sensors presents significant challenges due to their high deformability and intricate optical properties. To address these issues and enable a physically accurate simulation, we propose DOT-Sim: Differentiable Optical Tactile Simulation. Unlike prior simulators that rely on simplified models of deformable sensors, DOT-Sim accurately captures the physical behavior of soft sensors by modeling them as elastic materials using the Material Point Method (MPM). DOT-Sim enables rapid calibration of optical tactile sensor simulation using a small number of demonstrations within minutes, which is substantially faster than existing methods. Compared to current baselines, our approach supports much larger and non-linear deformations. To handle the optical aspect, we propose a novel approach to simulating optical responses by learning a residual image relative to the real-world idle state. We validate the physical and visual realism of our method through a series of zero-shot sim-to-real tasks. Our experiments show that DOT-Sim (1) accurately replicates the physical dynamics of a DenseTact optical tactile sensor in reality, (2) generates realistic optical outputs in contact-rich scenarios, (3) enables direct deployment of simulation-trained classifiers in the real world, achieving 85% classification accuracy on challenging objects and 90% accuracy in embedded tumor-type detection, and (4) allows precise trajectory following with a policy trained from demonstrations in simulation, with an average error of less than 0.9 mm.

cs.RO↗

arXiv2026

Rodrigues Network for Learning Robot Actions

Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the underlying kinematic structure of articulated systems. To this end, we propose the Neural Rodrigues Operator, a learnable generalization of the classical forward kinematics operation, designed to inject kinematics-aware inductive bias into neural computation. Building on this operator, we design the Rodrigues Network (RodriNet), a novel neural architecture specialized for processing actions. We evaluate the expressivity of our network on two synthetic tasks on kinematic and motion prediction, showing significant improvements compared to standard backbones. We further demonstrate its effectiveness in two realistic applications: (i) imitation learning on robotic benchmarks with the Diffusion Policy, and (ii) single-image 3D hand reconstruction. Our results suggest that integrating structured kinematic priors into the network architecture improves action learning in various domains.

cs.RO↗

arXiv2026

R2E-VID: Two-Stage Robust Routing via Temporal Gating for Elastic Edge-Cloud Video Inference

With the rapid growth of large-scale video analytics applications, edge-cloud collaborative systems have become the dominant paradigm for real-time inference. However, existing approaches often fail to dynamically adapt to heterogeneous video content and fluctuating resource conditions, resulting in suboptimal routing efficiency and high computational costs. In this paper, we propose R2E-VID, a two-stage robust routing framework via temporal gating for elastic edge-cloud video inference. In the first stage, R2E-VID introduces a temporal gating mechanism that models the temporal consistency and motion dynamics of incoming video streams to predict the optimal routing pattern for each segment. This enables adaptive partitioning of inference workloads between edge and cloud nodes, achieving fine-grained spatiotemporal elasticity. In the second stage, a robust routing optimization module refines the allocation through multi-model adaptation, jointly minimizing inference delay and resource consumption under dynamic network and workload variations. Extensive experiments on public datasets demonstrate that R2E-VID achieves up to 60% reduction in overall cost compared to cloud-centric baselines, and delivers 35-45% lower delay while improving inference accuracy by 2-7% over state-of-the-art edge-cloud solutions.

cs.NI↗

arXiv2026

SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling

Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-thought generation. However, RL training efficiency is often bottlenecked by the rollout phase, which can account for up to 70% of total training time when generating long trajectories (e.g., 16k tokens), due to slow autoregressive generation and synchronization overhead between rollout and policy updates. We propose SortedRL, an online length-aware scheduling strategy designed to address this bottleneck by improving rollout efficiency and maintaining training stability. SortedRL reorders rollout samples based on output lengths, prioritizing short samples forming groups for early updates. This enables large rollout batches, flexible update batches, and near on-policy micro-curriculum construction simultaneously. To further accelerate the pipeline, SortedRL incorporates a mechanism to control the degree of off-policy training through a cache-based mechanism, and is supported by a dedicated RL infrastructure that manages rollout and update via a stateful controller and rollout buffer. Experiments using LLaMA-3.1-8B and Qwen-2.5-32B on diverse tasks, including logical puzzles, and math challenges like AIME 24, Math 500, and Minerval, show that SortedRL reduces RL training bubble ratios by over 50%, while attaining 3.9% to 18.4% superior performance over baseline given same amount of data.

cs.LG↗

arXiv2026

Neural Value Iteration

The value function of a POMDP exhibits the piecewise-linear-convex (PWLC) property and can be represented as a finite set of hyperplanes, known as $α$-vectors. Most state-of-the-art POMDP solvers (offline planners) follow the point-based value iteration scheme, which performs Bellman backups on $α$-vectors at reachable belief points until convergence. However, since each $α$-vector is $|S|$-dimensional, these methods quickly become intractable for large-scale problems due to the prohibitive computational cost of Bellman backups. In this work, we demonstrate that the PWLC property allows a POMDP's value function to be alternatively represented as a finite set of neural networks. This insight enables a novel POMDP planning algorithm called \emph{Neural Value Iteration}, which combines the generalization capability of neural networks with the classical value iteration framework. Our approach achieves near-optimal solutions even in extremely large POMDPs that are intractable for existing offline solvers.

cs.AI↗

arXiv2026

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Video generation models have achieved remarkable progress in the past year. The quality of AI video continues to improve, but at the cost of larger model size, increased data quantity, and greater demand for training compute. In this report, we present Open-Sora 2.0, a commercial-level video generation model trained for only $200k. With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable. We detail all techniques that contribute to this efficiency breakthrough, including data curation, model architecture, training strategy, and system optimization. According to human evaluation results and VBench scores, Open-Sora 2.0 is comparable to global leading video generation models including the open-source HunyuanVideo and the closed-source Runway Gen-3 Alpha. By making Open-Sora 2.0 fully open-source, we aim to democratize access to advanced video generation technology, fostering broader innovation and creativity in content creation. All resources are publicly available at: https://github.com/hpcaitech/Open-Sora.

cs.GR↗

arXiv2026

MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE

Mixture-of-Experts (MoE) enables efficient scaling of large language models by activating only a subset of experts per input token. However, deploying MoE-based models incurs significant memory overhead due to the need to retain all experts in memory. While structured pruning is promising to reduce memory costs, existing methods often show suboptimal performance and unstable degradation in three dimensions: model architectures, calibration data sources, and calibration sample sizes. This paper proposes Mixture-of-Novices-and-Experts (MoNE), a novel expert pruning method that replaces redundant experts with lightweight novices to achieve effective and robust model compression. MoNE evaluates expert redundancy based on two metrics: access frequency and output variance. Experts exhibiting low usage and stable outputs are pruned and replaced with lightweight novices-unbiased estimations of their original outputs-minimizing performance degradation. Extensive experiments demonstrate that MoNE consistently outperforms baseline methods with minimal accuracy degradation across the three dimensions, confirming its effectiveness and robustness. Notably, it outperforms baselines by up to 2.72 for the average zero shot accuracy across nine downstream tasks under 25% pruning ratio, with only 0.14 performance drop for Qwen2-57B-A14B. The code is available at https://github.com/zxgx/mode-pd.

cs.LG↗

arXiv2026

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning

While fine-tuning large language models (LLMs) for specific tasks often yields impressive results, it comes at the cost of memory inefficiency due to back-propagation in gradient-based training. Memory-efficient Zeroth-order (MeZO) optimizers, recently proposed to address this issue, only require forward passes during training, making them more memory-friendly. However, compared with exact gradients, ZO-based gradients usually exhibit an estimation error, which can significantly hurt the optimization process, leading to slower convergence and suboptimal solutions. In addition, we find that the estimation error will hurt more when adding to large weights instead of small weights. Based on this observation, this paper introduces Sparse MeZO, a novel memory-efficient zeroth-order optimization approach that applies ZO only to a carefully chosen subset of parameters. We propose a simple yet effective parameter selection scheme that yields significant performance gains with Sparse-MeZO. Additionally, we develop a memory-optimized implementation for sparse masking, ensuring the algorithm requires only inference-level memory consumption, allowing Sparse-MeZO to fine-tune LLaMA-30b on a single A100 GPU. Experimental results illustrate that Sparse-MeZO consistently improves both performance and convergence speed over MeZO without any overhead. For example, it achieves a 9\% absolute accuracy improvement and 3.5x speedup over MeZO on the RTE task. Code is available at https://github.com/NUS-HPC-AI-Lab/SparseMeZO.

cs.LG↗

arXiv2026

K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge

The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human preference assessments by collecting human votes, they are costly and time-consuming, inherently limiting their scalability. Leveraging vision-language model (VLMs) as substitutes for manual judgments presents a promising solution. However, the inherent hallucinations and biases of VLMs hinder alignment with human preferences, thus compromising evaluation reliability. Additionally, the static evaluation approach lead to low efficiency. In this paper, we propose K-Sort Eval, a reliable and efficient VLM-based evaluation framework that integrates posterior correction and dynamic matching. Specifically, we curate a high-quality dataset from thousands of human votes in K-Sort Arena, with each instance containing the outputs and rankings of K models. When evaluating a new model, it undergoes (K+1)-wise free-for-all comparisons with existing models, and the VLM provide the rankings. To enhance alignment and reliability, we propose a posterior correction method, which adaptively corrects the posterior probability in Bayesian updating based on the consistency between the VLM prediction and human supervision. Moreover, we propose a dynamic matching strategy, which balances uncertainty and diversity to maximize the expected benefit of each comparison, thus ensuring more efficient evaluation. Extensive experiments show that K-Sort Eval delivers evaluation results consistent with K-Sort Arena, typically requiring fewer than 90 model runs, demonstrating both its efficiency and reliability.

cs.CV↗

arXiv2026

DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion

Current speech language models generate responses directly without explicit reasoning, leading to errors that cannot be corrected once audio is produced. We introduce \textbf{``Silent Thought, Spoken Answer''} -- a paradigm where speech LLMs generate internal text reasoning alongside spoken responses, with thinking traces informing speech quality. To realize this, we present \method{}, the first diffusion-based speech-text language model supporting both understanding and generation, unifying discrete text and tokenized speech under a single masked diffusion framework. Unlike autoregressive approaches, \method{} jointly generates reasoning traces and speech tokens through iterative denoising, with modality-specific masking schedules. We also construct \dataset{}, the first speech QA dataset with paired text reasoning traces, containing 26K samples totaling 319 hours. Experiments show \method{} achieves state-of-the-art speech-to-speech QA accuracy, outperforming the best baseline by up to 9 points, while attaining the best TTS quality among generative models (6.2\% WER) and preserving language understanding (66.2\% MMLU). Ablations confirm that both the diffusion architecture and thinking traces contribute to these gains.

cs.CL↗

arXiv2026

MoST: Mixing Speech and Text with Modality-Aware Mixture of Experts

We present MoST (Mixture of Speech and Text), a novel multimodal large language model that seamlessly integrates speech and text processing through our proposed Modality-Aware Mixture of Experts (MAMoE) architecture. While current multimodal models typically process diverse modality representations with identical parameters, disregarding their inherent representational differences, we introduce specialized routing pathways that direct tokens to modality-appropriate experts based on input type. MAMoE simultaneously enhances modality-specific learning and cross-modal understanding through two complementary components: modality-specific expert groups that capture domain-specific patterns and shared experts that facilitate information transfer between modalities. Building on this architecture, we develop an efficient transformation pipeline that adapts the pretrained MoE language model through strategic post-training on ASR and TTS datasets, followed by fine-tuning with a carefully curated speech-text instruction dataset. A key feature of this pipeline is that it relies exclusively on fully accessible, open-source datasets to achieve strong performance and data efficiency. Comprehensive evaluations across ASR, TTS, audio language modeling, and spoken question answering benchmarks show that MoST consistently outperforms existing models of comparable parameter counts. Our ablation studies confirm that the modality-specific routing mechanism and shared experts design significantly contribute to performance gains across all tested domains. To our knowledge, MoST represents the first fully open-source speech-text LLM built on a Mixture of Experts architecture. \footnote{We release MoST model, training code, inference code, and training data at https://github.com/NUS-HPC-AI-Lab/MoST

cs.CL↗

arXiv2026

DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation

Diffusion Transformer (DiT), an emerging diffusion model for visual generation, has demonstrated superior performance but suffers from substantial computational costs. Our investigations reveal that these costs primarily stem from the static inference paradigm, which inevitably introduces redundant computation in certain diffusion timesteps and spatial regions. To overcome this inefficiency, we propose Dynamic Diffusion Transformer (DyDiT), an architecture that dynamically adjusts its computation along both timestep and spatial dimensions. Building on these designs, we present an extended version, DyDiT++, with improvements in three key aspects. First, it extends the generation mechanism of DyDiT beyond diffusion to flow matching, demonstrating that our method can also accelerate flow-matching-based generation, enhancing its versatility. Furthermore, we enhance DyDiT to tackle more complex visual generation tasks, including video generation and text-to-image generation, thereby broadening its real-world applications. Finally, to address the high cost of full fine-tuning and democratize technology access, we investigate the feasibility of training DyDiT in a parameter-efficient manner and introduce timestep-based dynamic LoRA (TD-LoRA). Extensive experiments on diverse visual generation models, including DiT, SiT, Latte, and FLUX, demonstrate the effectiveness of DyDiT++. Remarkably, with <3% additional fine-tuning iterations, our approach reduces the FLOPs of DiT-XL by 51%, yielding 1.73x realistic speedup on hardware, and achieves a competitive FID score of 2.07 on ImageNet. The code is available at https://github.com/alibaba-damo-academy/DyDiT.

cs.CV↗

arXiv2026

Neural-Driven Image Editing

Traditional image editing typically relies on manual prompting, making it labor-intensive and inaccessible to individuals with limited motor control or language abilities. Leveraging recent advances in brain-computer interfaces (BCIs) and generative models, we propose LoongX, a hands-free image editing approach driven by multimodal neurophysiological signals. LoongX utilizes state-of-the-art diffusion models trained on a comprehensive dataset of 23,928 image editing pairs, each paired with synchronized electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), photoplethysmography (PPG), and head motion signals that capture user intent. To effectively address the heterogeneity of these signals, LoongX integrates two key modules. The cross-scale state space (CS3) module encodes informative modality-specific features. The dynamic gated fusion (DGF) module further aggregates these features into a unified latent space, which is then aligned with edit semantics via fine-tuning on a diffusion transformer (DiT). Additionally, we pre-train the encoders using contrastive learning to align cognitive states with semantic intentions from embedded natural language. Extensive experiments demonstrate that LoongX achieves performance comparable to text-driven methods (CLIP-I: 0.6605 vs. 0.6558; DINO: 0.4812 vs. 0.4636) and outperforms them when neural signals are combined with speech (CLIP-T: 0.2588 vs. 0.2549). These results highlight the promise of neural-driven generative models in enabling accessible, intuitive image editing and open new directions for cognitive-driven creative technologies. The code and dataset are released on the project website: https://loongx1.github.io.

cs.CV↗

arXiv2025

FOCUS: Efficient Keyframe Selection for Long Video Understanding

Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelines therefore either uniformly subsample or apply keyframe selection with retrieval-style scoring using smaller vision-language models. However, these keyframe selection methods still rely on pre-filtering before selection to reduce the inference cost and can miss the most informative moments. We propose FOCUS, Frame-Optimistic Confidence Upper-bound Selection, a training-free, model-agnostic keyframe selection module that selects query-relevant frames under a strict token budget. FOCUS formulates keyframe selection as a combinatorial pure-exploration (CPE) problem in multi-armed bandits: it treats short temporal clips as arms, and uses empirical means and Bernstein confidence radius to identify informative regions while preserving exploration of uncertain areas. The resulting two-stage exploration-exploitation procedure reduces from a sequential policy with theoretical guarantees, first identifying high-value temporal regions, then selecting top-scoring frames within each region. On two long-video question-answering benchmarks, FOCUS delivers substantial accuracy improvements while processing less than 2% of video frames. For videos longer than 20 minutes, it achieves an 11.9% gain in accuracy on LongVideoBench, demonstrating its effectiveness as a keyframe selection method and providing a simple and general solution for scalable long-video understanding with MLLMs. Code is available at https://github.com/NUS-HPC-AI-Lab/FOCUS.

cs.CV↗

arXiv2025

V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models

Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.

cs.CV↗

arXiv2025

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and heterogeneous workloads -- introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) latency and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2x and achieving 3.2-4.5x higher throughput while meeting service-level objectives (SLOs).

cs.DC↗