arXiv subjects

Yang Gao

Publications and source records attributed to Yang Gao.

At least 199 records · Page 11Linked to original sources

arXiv2025

RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation

Enabling robots to flexibly schedule and compose learned skills for novel long-horizon manipulation under diverse perturbations remains a core challenge. Early explorations with end-to-end VLA models show limited success, as these models struggle to generalize beyond the training distribution. Hierarchical approaches, where high-level planners generate subgoals for low-level policies, bring certain improvements but still suffer under complex perturbations, revealing limited capability in skill composition. However, existing benchmarks primarily emphasize task completion in long-horizon settings, offering little insight into compositional generalization, robustness, and the interplay between planning and execution. To systematically investigate these gaps, we propose RoboHiMan, a hierarchical evaluation paradigm for compositional generalization in long-horizon manipulation. RoboHiMan introduces HiMan-Bench, a benchmark of atomic and compositional tasks under diverse perturbations, supported by a multi-level training dataset for analyzing progressive data scaling, and proposes three evaluation paradigms (vanilla, decoupled, coupled) that probe the necessity of skill composition and reveal bottlenecks in hierarchical architectures. Experiments highlight clear capability gaps across representative models and architectures, pointing to directions for advancing models better suited to real-world long-horizon manipulation tasks. Videos and open-source code can be found on our project website: https://chenyt31.github.io/robo-himan.github.io/.

cs.RO↗

arXiv2025

Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation

Current autoregressive diffusion models excel at video generation but are generally limited to short temporal durations. Our theoretical analysis indicates that the autoregressive modeling typically suffers from temporal drift caused by error accumulation and hinders parallelization in long video synthesis. To address these limitations, we propose a novel planning-then-populating framework centered on Macro-from-Micro Planning (MMPL) for long video generation. MMPL sketches a global storyline for the entire video through two hierarchical stages: Micro Planning and Macro Planning. Specifically, Micro Planning predicts a sparse set of future keyframes within each short video segment, offering motion and appearance priors to guide high-quality video segment generation. Macro Planning extends the in-segment keyframes planning across the entire video through an autoregressive chain of micro plans, ensuring long-term consistency across video segments. Subsequently, MMPL-based Content Populating generates all intermediate frames in parallel across segments, enabling efficient parallelization of autoregressive generation. The parallelization is further optimized by Adaptive Workload Scheduling for balanced GPU execution and accelerated autoregressive video generation. Extensive experiments confirm that our method outperforms existing long video generation models in quality and stability. Generated videos and comparison results are in our project page.

cs.CV↗

arXiv2025

On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning

Continual learning seeks the human-like ability to accumulate new skills in machine intelligence. Its central challenge is catastrophic forgetting, whose underlying cause has not been fully understood for deep networks. In this paper, we demystify catastrophic forgetting by revealing that the new-task training is implicitly an adversarial attack against the old-task knowledge. Specifically, the new-task gradients automatically and accurately align with the sharp directions of the old-task loss landscape, rapidly increasing the old-task loss. This adversarial alignment is intriguingly counter-intuitive because the sharp directions are too sparsely distributed to align with by chance. To understand it, we theoretically show that it arises from training's low-rank bias, which, through forward and backward propagation, confines the two directions into the same low-dimensional subspace, facilitating alignment. Gradient projection (GP) methods, a representative family of forgetting-mitigating methods, reduce adversarial alignment caused by forward propagation, but cannot address the alignment due to backward propagation. We propose backGP to address it, which reduces forgetting by 10.8% and improves accuracy by 12.7% on average over GP methods.

cs.LG↗

arXiv2025

Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

We propose Stable Video Infinity (SVI) that is able to generate infinite-length videos with high temporal consistency, plausible scene transitions, and controllable streaming storylines. While existing long-video methods attempt to mitigate accumulated errors via handcrafted anti-drifting (e.g., modified noise scheduler, frame anchoring), they remain limited to single-prompt extrapolation, producing homogeneous scenes with repetitive motions. We identify that the fundamental challenge extends beyond error accumulation to a critical discrepancy between the training assumption (seeing clean data) and the test-time autoregressive reality (conditioning on self-generated, error-prone outputs). To bridge this hypothesis gap, SVI incorporates Error-Recycling Fine-Tuning, a new type of efficient training that recycles the Diffusion Transformer (DiT)'s self-generated errors into supervisory prompts, thereby encouraging DiT to actively identify and correct its own errors. This is achieved by injecting, collecting, and banking errors through closed-loop recycling, autoregressively learning from error-injected feedback. Specifically, we (i) inject historical errors made by DiT to intervene on clean inputs, simulating error-accumulated trajectories in flow matching; (ii) efficiently approximate predictions with one-step bidirectional integration and calculate errors with residuals; (iii) dynamically bank errors into replay memory across discretized timesteps, which are resampled for new input. SVI is able to scale videos from seconds to infinite durations with no additional inference cost, while remaining compatible with diverse conditions (e.g., audio, skeleton, and text streams). We evaluate SVI on three benchmarks, including consistent, creative, and conditional settings, thoroughly verifying its versatility and state-of-the-art role.

cs.CV↗

arXiv2025

Precision Measurement of the Branching Fraction of $D^{+}\to μ^{+}ν_μ$

Using $20.3~\mathrm{fb}^{-1}$ of $e^+e^-$ collision data collected at a center-of-mass energy of $E_{\rm c.m.}=3.773$ GeV with the BESIII detector operating at the BEPCII collider, we determine the branching fraction of the leptonic decay $D^+\toμ^+ν_μ$ to be $(4.034\pm0.080_{\rm stat}\pm0.040_{\rm syst})\times10^{-4}$. Interpreting our measurement with knowledge of the Fermi coupling constant $G_F$, the masses of the $D^+$ and $μ^+$ as well as the lifetime of the $D^+$, we determine $f_{D^+}|V_{cd}|=(48.02\pm0.48_{\rm stat}\pm0.24_{\rm syst}\pm0.12_{\rm input}\pm0.15_{\rm EM})~\mathrm{MeV}$ after taking into account necessary radiative corrections. This result is a factor of 2.3 more precise than the previous best measurement. Using the value of the magnitude of the $c\to d$ Cabibbo-Kobayashi-Maskawa matrix element $|V_{cd}|$ given by the global standard model fit, we obtain the $D^+$ decay constant $f_{D^+}=(213.5\pm2.1_{\rm stat}\pm1.1_{\rm syst}\pm0.8_{\rm input}\pm0.7_{\rm EM})$\,MeV. Alternatively, using the value of $f_{D^+}$ from a precise lattice quantum chromodynamics calculation, we extract $|V_{cd}|=0.2265\pm0.0023_{\rm stat}\pm0.0011_{\rm syst}\pm0.0009_{\rm input}\pm0.0007_{\rm EM}$.

hep-ex↗

arXiv2025

Distributed Algorithms for Multi-Agent Multi-Armed Bandits with Collision

We study the stochastic Multiplayer Multi-Armed Bandit (MMAB) problem, where multiple players select arms to maximize their cumulative rewards. Collisions occur when two or more players select the same arm, resulting in no reward, and are observed by the players involved. We consider a distributed setting without central coordination, where each player can only observe their own actions and collision feedback. We propose a distributed algorithm with an adaptive, efficient communication protocol. The algorithm achieves near-optimal group and individual regret, with a communication cost of only $\mathcal{O}(\log\log T)$. Our experiments demonstrate significant performance improvements over existing baselines. Compared to state-of-the-art (SOTA) methods, our approach achieves a notable reduction in individual regret. Finally, we extend our approach to a periodic asynchronous setting, proving the lower bound for this problem and presenting an algorithm that achieves logarithmic regret.

cs.LG↗

arXiv2025

Wrist2Finger: Sensing Fingertip Force for Force-Aware Hand Interaction with a Ring-Watch Wearable

Hand pose tracking is essential for advancing applications in human-computer interaction. Current approaches, such as vision-based systems and wearable devices, face limitations in portability, usability, and practicality. We present a novel wearable system that reconstructs 3D hand pose and estimates per-finger forces using a minimal ring-watch sensor setup. A ring worn on the finger integrates an inertial measurement unit (IMU) to capture finger motion, while a smartwatch-based single-channel electromyography (EMG) sensor on the wrist detects muscle activations. By leveraging the complementary strengths of motion sensing and muscle signals, our approach achieves accurate hand pose tracking and grip force estimation in a compact wearable form factor. We develop a dual-branch transformer network that fuses IMU and EMG data with cross-modal attention to predict finger joint positions and forces simultaneously. A custom loss function imposes kinematic constraints for smooth force variation and realistic force saturation. Evaluation with 20 participants performing daily object interaction gestures demonstrates an average Mean Per Joint Position Error (MPJPE) of 0.57 cm and a fingertip force estimation (RMSE: 0.213, r=0.76). We showcase our system in a real-time Unity application, enabling virtual hand interactions that respond to user-applied forces. This minimal, force-aware tracking system has broad implications for VR/AR, assistive prosthetics, and ergonomic monitoring.

cs.HC↗

arXiv2025

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits expressivity. Recent end-to-end methods reduce latency and better preserve these cues, yet still rely on text intermediates, creating a fundamental bottleneck. We present MOSS-Speech, a true speech-to-speech large language model that directly understands and generates speech without relying on text guidance. Our approach combines a modality-based layer-splitting architecture with a frozen pre-training strategy, preserving the reasoning and knowledge of pretrained text LLMs while adding native speech capabilities. Experiments show that our model achieves state-of-the-art results in spoken question answering and delivers comparable speech-to-speech performance relative to existing text-guided systems, while still maintaining competitive text performance. By narrowing the gap between text-guided and direct speech generation, our work establishes a new paradigm for expressive and efficient end-to-end speech interaction.

cs.CL↗

arXiv2025

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widespread distillation and deployment of large language models (LLMs) into single file .gguf formats, their weight spaces have become exposed to an unprecedented hardware attack surface. This paper is the first to systematically discover and validate the existence of single-bit vulnerabilities in LLM weight files: in mainstream open-source models (e.g., DeepSeek and QWEN) using .gguf quantized formats, flipping just single bit can induce three types of targeted semantic level failures Artificial Flawed Intelligence (outputting factual errors), Artificial Weak Intelligence (degradation of logical reasoning capability), and Artificial Bad Intelligence (generating harmful content). By building an information theoretic weight sensitivity entropy model and a probabilistic heuristic scanning framework called BitSifter, we achieved efficient localization of critical vulnerable bits in models with hundreds of millions of parameters. Experiments show that vulnerabilities are significantly concentrated in the tensor data region, particularly in areas related to the attention mechanism and output layers, which are the most sensitive. A negative correlation was observed between model size and robustness, with smaller models being more susceptible to attacks. Furthermore, a remote BFA chain was designed, enabling semantic-level attacks in real-world environments: At an attack frequency of 464.3 times per second, a single bit can be flipped with 100% success in as little as 31.7 seconds. This causes the accuracy of LLM to plummet from 73.5% to 0%, without requiring high-cost equipment or complex prompt engineering.

cs.CR↗

arXiv2025

Best of Sim and Real: Decoupled Visuomotor Manipulation via Learning Control in Simulation and Perception in Real

Sim-to-real transfer remains a fundamental challenge in robot manipulation due to the entanglement of perception and control in end-to-end learning. We present a decoupled framework that learns each component where it is most reliable: control policies are trained in simulation with privileged state to master spatial layouts and manipulation dynamics, while perception is adapted only at deployment to bridge real observations to the frozen control policy. Our key insight is that control strategies and action patterns are universal across environments and can be learned in simulation through systematic randomization, while perception is inherently domain-specific and must be learned where visual observations are authentic. Unlike existing end-to-end approaches that require extensive real-world data, our method achieves strong performance with only 10-20 real demonstrations by reducing the complex sim-to-real problem to a structured perception alignment task. We validate our approach on tabletop manipulation tasks, demonstrating superior data efficiency and out-of-distribution generalization compared to end-to-end baselines. The learned policies successfully handle object positions and scales beyond the training distribution, confirming that decoupling perception from control fundamentally improves sim-to-real transfer.

cs.RO↗

arXiv2025

Typhoon Tracks Regulated by Feedbacks of Fine-Scale Clouds to Environment

Accurate tropical cyclone (TC) track prediction is crucial for mitigating the catastrophic impacts of TCs on human life and the environment. Despite decades of research on tropical cyclone (TC) track prediction, large errors known as track forecast busts (TFBs) occur frequently, and their causes remain poorly understood. Here, we examine a few dozens of TCs using a unique TC downscaling strategy that can quantitatively assess the sensitivity of TC track on the strength of feedbacks of fine-scale clouds to environment. We show that as TFBs have a weaker environmental steering that favors scattering cumulonimbus clouds, capturing asymmetric distribution of planetary vorticity advection induced by such fine-scale clouds corrects TFBs by 60 percent. Our clear identification of such important TC track predictability source promises continuous improvement of TC track prediction as finer-scale TC clouds and their interactions with environment are better resolved as model larger-scale behaviors have improved.

physics.ao-ph↗

arXiv2025

An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering

Recently, some works integrate SSL techniques into deep clustering frameworks to enhance image clustering performance. However, they all need pretraining, clustering learning, or a trained clustering model as prerequisites, limiting the flexible and out-of-box application of SSL learners in the image clustering task. This work introduces ASD, an adaptor that enables the cold-start of SSL learners for deep image clustering without any prerequisites. Specifically, we first randomly sample pseudo-labeled data from all unlabeled data, and set an instance-level classifier to learn them with semantically aligned instance-level labels. With the ability of instance-level classification, we track the class transitions of predictions on unlabeled data to extract high-level similarities of instance-level classes, which can be utilized to assign cluster-level labels to pseudo-labeled data. Finally, we use the pseudo-labeled data with assigned cluster-level labels to trigger a general SSL learner trained on the unlabeled data for image clustering. We show the superior performance of ASD across various benchmarks against the latest deep image clustering approaches and very slight accuracy gaps compared to SSL methods using ground-truth, e.g., only 1.33% on CIFAR-10. Moreover, ASD can also further boost the performance of existing SSL-embedded deep image clustering methods.

cs.CV↗

arXiv2025

Do You Need Proprioceptive States in Visuomotor Policies?

Imitation-learning-based visuomotor policies have been widely used in robot manipulation, where both visual observations and proprioceptive states are typically adopted together for precise control. However, in this study, we find that this common practice makes the policy overly reliant on the proprioceptive state input, which causes overfitting to the training trajectories and results in poor spatial generalization. On the contrary, we propose the State-free Policy, removing the proprioceptive state input and predicting actions only conditioned on visual observations. The State-free Policy is built in the relative end-effector action space, and should ensure the full task-relevant visual observations, here provided by dual wide-angle wrist cameras. Empirical results demonstrate that the State-free policy achieves significantly stronger spatial generalization than the state-based policy: in real-world tasks such as pick-and-place, challenging shirt-folding, and complex whole-body manipulation, spanning multiple robot embodiments, the average success rate improves from 0% to 85% in height generalization and from 6% to 64% in horizontal generalization. Furthermore, they also show advantages in data efficiency and cross-embodiment adaptation, enhancing their practicality for real-world deployment. Discover more by visiting: https://statefreepolicy.github.io.

cs.RO↗

arXiv2025

Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI

Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Embodied AI, making research lack clear objectives; (2) absence of unified and standardized evaluation systems, rendering cross-benchmark evaluation infeasible; and (3) underdeveloped automated and scalable acquisition methods for embodied data, creating critical bottlenecks for model scaling. To address these obstacles, we present Embodied Arena, a comprehensive, unified, and evolving evaluation platform for Embodied AI. Our platform establishes a systematic embodied capability taxonomy spanning three levels (perception, reasoning, task execution), seven core capabilities, and 25 fine-grained dimensions, enabling unified evaluation with systematic research objectives. We introduce a standardized evaluation system built upon unified infrastructure supporting flexible integration of 22 diverse benchmarks across three domains (2D/3D Embodied Q&A, Navigation, Task Planning) and 30+ advanced models from 20+ worldwide institutes. Additionally, we develop a novel LLM-driven automated generation pipeline ensuring scalable embodied evaluation data with continuous evolution for diversity and comprehensiveness. Embodied Arena publishes three real-time leaderboards (Embodied Q&A, Navigation, Task Planning) with dual perspectives (benchmark view and capability view), providing comprehensive overviews of advanced model capabilities. Especially, we present nine findings summarized from the evaluation results on the leaderboards of Embodied Arena. This helps to establish clear research veins and pinpoint critical research problems, thereby driving forward progress in the field of Embodied AI.

cs.RO↗

arXiv2025

ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancement

Diffusion-based speech enhancement (SE) achieves natural-sounding speech and strong generalization, yet suffers from key limitations like generative artifacts and high inference latency. In this work, we systematically study artifact prediction and reduction in diffusion-based SE. We show that variance in speech embeddings can be used to predict phonetic errors during inference. Building on these findings, we propose an ensemble inference method guided by semantic consistency across multiple diffusion runs. This technique reduces WER by 15% in low-SNR conditions, effectively improving phonetic accuracy and semantic plausibility. Finally, we analyze the effect of the number of diffusion steps, showing that adaptive diffusion steps balance artifact suppression and latency. Our findings highlight semantic priors as a powerful tool to guide generative SE toward artifact-free outputs.

cs.SD↗

arXiv2025

MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies

Scaling real robot data is a key bottleneck in imitation learning, leading to the use of auxiliary data for policy training. While other aspects of robotic manipulation such as image or language understanding may be learned from internet-based datasets, acquiring motion knowledge remains challenging. Human data, with its rich diversity of manipulation behaviors, offers a valuable resource for this purpose. While previous works show that using human data can bring benefits, such as improving robustness and training efficiency, it remains unclear whether it can realize its greatest advantage: enabling robot policies to directly learn new motions for task completion. In this paper, we systematically explore this potential through multi-task human-robot cotraining. We introduce MotionTrans, a framework that includes a data collection system, a human data transformation pipeline, and a weighted cotraining strategy. By cotraining 30 human-robot tasks simultaneously, we direcly transfer motions of 13 tasks from human data to deployable end-to-end robot policies. Notably, 9 tasks achieve non-trivial success rates in zero-shot manner. MotionTrans also significantly enhances pretraining-finetuning performance (+40% success rate). Through ablation study, we also identify key factors for successful motion learning: cotraining with robot data and broad task-related motion coverage. These findings unlock the potential of motion-level learning from human data, offering insights into its effective use for training robotic manipulation policies. All data, code, and model weights are open-sourced https://motiontrans.github.io/.

cs.RO↗

arXiv2025

Empathy-R1: A Chain-of-Empathy and Reinforcement Learning Framework for Long-Form Mental Health Support

Empathy is critical for effective mental health support, especially when addressing Long Counseling Texts (LCTs). However, existing Large Language Models (LLMs) often generate replies that are semantically fluent but lack the structured reasoning necessary for genuine psychological support, particularly in a Chinese context. To bridge this gap, we introduce Empathy-R1, a novel framework that integrates a Chain-of-Empathy (CoE) reasoning process with Reinforcement Learning (RL) to enhance response quality for LCTs. Inspired by cognitive-behavioral therapy, our CoE paradigm guides the model to sequentially reason about a help-seeker's emotions, causes, and intentions, making its thinking process both transparent and interpretable. Our framework is empowered by a new large-scale Chinese dataset, Empathy-QA, and a two-stage training process. First, Supervised Fine-Tuning instills the CoE's reasoning structure. Subsequently, RL, guided by a dedicated reward model, refines the therapeutic relevance and contextual appropriateness of the final responses. Experiments show that Empathy-R1 achieves strong performance on key automatic metrics. More importantly, human evaluations confirm its superiority, showing a clear preference over strong baselines and achieving a Win@1 rate of 44.30% on our new benchmark. By enabling interpretable and contextually nuanced responses, Empathy-R1 represents a significant advancement in developing responsible and genuinely beneficial AI for mental health support.

cs.CL↗

arXiv2025

Anomalous-Hall Neel textures in altermagnetic materials

Recently, the altermagnets, a new kind of collinear antiferromagnet with nearly zero net magnetization and momentum-dependent spin-splitting of bands, have sparked great interest. Despite simple magnetic structures, these altermagnets exhibit intriguing and intricate dependence of anomalous Hall effect (AHE) on the Néel vector, in contrast to the conventional perpendicular configuration of Hall current with magnetization in ferromagnets. However, the fundamental relationship between the AHE and the Néel vector remains largely elusive. Here, we reveal all the unconventional anomalous Hall textures in the Néel vector space, dubbed anomalous-Hall Néel textures (AHNTs) for altermagnets. Specifically, we identify 10 types across four categories of AHNTs for all altermagnets. Notably, we find that AHNTs resemble the known spin textures in momentum space, and further reveal their symmetry origin. Meanwhile, we examine our key discoveries in prototypical altermagnets. Our work offers a thorough understanding of AHE in altermagnets and a complete and pictorial classification of altermagnets based on the geometry of response functions.

cond-mat.mtrl-sci↗