Institution profile

GigaAI

Industry researchasia · cn
Official website
Research library51linked papers
Opportunities0open roles
Selected work

Representative Papers

STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching

Jul 22, 2026

This work addresses the limitations of traditional stereo matching methods, which model disparity estimation as deterministic regression and consequently struggle with multimodal distributions and ambiguous regions, often yielding mean bias. To overcome this, the paper introduces the first generative stereo matching framework that unifies deterministic regression with probabilistic distribution modeling. The approach leverages a two-stage progressive cascaded network, a frequency-decoupled StereoDiT pixel diffusion Transformer, and a novel Transition Flow Matching optimization objective to enable efficient few-step generation. The proposed method achieves state-of-the-art performance across multiple benchmarks—including Scene Flow, KITTI, ETH3D, and Middlebury—and demonstrates exceptional zero-shot generalization, significantly improving detail fidelity and consistency in geometrically discontinuous and textureless regions.

0 citationsRead paper

PhysClaw-0: A Symbiotic Agentic System for Robot Autonomy via Language Corrections

Jul 15, 2026

This work addresses the escalating human supervision cost in robotic autonomous data collection, where repeated human corrections for recurring failure modes lead to linearly increasing labor demands over task duration. To overcome this limitation, the authors introduce PhysClaw-0, a human–robot symbiotic agent that enables cross-episode memory and reuse of natural language corrections for the first time. By leveraging a large language model to parse human instructions into structured adjustment policies, integrating a vision-language model as a verification module, and incorporating an autonomous reset mechanism, PhysClaw-0 forms a closed-loop data collection system that solicits human intervention only after exhausting retry attempts. Evaluated on a real-world tabletop clearing task, the approach reduces human effort to 16% of baseline levels, boosts single-attempt success rates from 12.5% to 47.5%, and achieves fine-tuning performance comparable to teleoperation-based training, substantially lowering long-term human labor costs.

0 citationsRead paper

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

Jul 05, 2026

This work addresses the challenge of end-effector misalignment or insertion failure in high-precision robotic manipulation caused by calibration inaccuracies, perception errors, and contact dynamics within world-action (WA) models. To overcome these limitations, the authors propose a hybrid attention-based latent-variable-guided online reinforcement learning framework. The approach integrates latent features and action priors from the WA model generation process through a lightweight actor-critic adapter, augmented with a hybrid attention mechanism that jointly captures task-relevant information from visual context and end-effector correction demands while preserving temporal consistency in actions. Evaluated on four real-world high-precision tasks, the method achieves an average success rate of 87.1%, surpassing the strongest baseline by 19.2 percentage points, with only 45–75 minutes of online training per task.

0 citationsRead paper
Recent publications

Latest Papers

STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matching

Jul 22, 2026

This work addresses the limitations of traditional stereo matching methods, which model disparity estimation as deterministic regression and consequently struggle with multimodal distributions and ambiguous regions, often yielding mean bias. To overcome this, the paper introduces the first generative stereo matching framework that unifies deterministic regression with probabilistic distribution modeling. The approach leverages a two-stage progressive cascaded network, a frequency-decoupled StereoDiT pixel diffusion Transformer, and a novel Transition Flow Matching optimization objective to enable efficient few-step generation. The proposed method achieves state-of-the-art performance across multiple benchmarks—including Scene Flow, KITTI, ETH3D, and Middlebury—and demonstrates exceptional zero-shot generalization, significantly improving detail fidelity and consistency in geometrically discontinuous and textureless regions.

0 citationsRead paper

PhysClaw-0: A Symbiotic Agentic System for Robot Autonomy via Language Corrections

Jul 15, 2026

This work addresses the escalating human supervision cost in robotic autonomous data collection, where repeated human corrections for recurring failure modes lead to linearly increasing labor demands over task duration. To overcome this limitation, the authors introduce PhysClaw-0, a human–robot symbiotic agent that enables cross-episode memory and reuse of natural language corrections for the first time. By leveraging a large language model to parse human instructions into structured adjustment policies, integrating a vision-language model as a verification module, and incorporating an autonomous reset mechanism, PhysClaw-0 forms a closed-loop data collection system that solicits human intervention only after exhausting retry attempts. Evaluated on a real-world tabletop clearing task, the approach reduces human effort to 16% of baseline levels, boosts single-attempt success rates from 12.5% to 47.5%, and achieves fine-tuning performance comparable to teleoperation-based training, substantially lowering long-term human labor costs.

0 citationsRead paper

HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models

Jul 05, 2026

This work addresses the challenge of end-effector misalignment or insertion failure in high-precision robotic manipulation caused by calibration inaccuracies, perception errors, and contact dynamics within world-action (WA) models. To overcome these limitations, the authors propose a hybrid attention-based latent-variable-guided online reinforcement learning framework. The approach integrates latent features and action priors from the WA model generation process through a lightweight actor-critic adapter, augmented with a hybrid attention mechanism that jointly captures task-relevant information from visual context and end-effector correction demands while preserving temporal consistency in actions. Evaluated on four real-world high-precision tasks, the method achieves an average success rate of 87.1%, surpassing the strongest baseline by 19.2 percentage points, with only 45–75 minutes of online training per task.

0 citationsRead paper