13 papers
Athanor: An Agent-Native System for Autonomous Post-Training Research
Yufa Zhou, Yichen Wang, Jiakun Fan +5
Recursive self-improvement, in which AI systems build stronger AI systems, is one promising route to superintelligence. We study a weaker form that can be measured today: frontier…
Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents
Xiyang Wu, Zhichao Liu, Shengxin zhang +4
Long-horizon agents often struggle to recover from failures whose causes lie several steps earlier, beyond what local reflection or backtracking can resolve. We introduce BELIEFWEA…
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Zongxia Li, Zhongzhi Li, Yucheng Shi +14
Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary che…
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
Jiakun Fan, Min Xiao, Qiang Wang +5
Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize proposal gener…
GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction
Ziyang Cheng, Tianshu Tang, Jinxin Lan +19
General-purpose motion trackers enable humanoid robots to follow diverse whole-body motions while maintaining balance, but are trained only on flat ground, failing to exploit biped…
GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Architecture
GigaBrain Team, Angen Ye, Axiang Sun +56
Vision-language-action (VLA) models have become a dominant paradigm for generalist embodied agents, demonstrating strong complex and long-horizon task completion in structured sett…
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi +12
AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely focus on simple problems that finish within minu…
GigaWorld-Policy: An Efficient Action-Centered World--Action Model
Angen Ye, Boyuan Wang, Chaojun Ni +21
World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches fac…
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Zongxia Li, Hongyang Du, Chengsong Huang +8
Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention…
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
GigaBrain Team, Boyuan Wang, Bohan Li +23
Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and we…
First Frame Is the Place to Go for Video Content Customization
Jingxi Chen, Zongxia Li, Zhichao Liu +6
What role does the first frame play in video generation models? Traditionally, it's viewed as the spatial-temporal starting point of a video, merely a seed for subsequent animation…
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
GigaBrain Team, Angen Ye, Boyuan Wang +24
Training Vision-Language-Action (VLA) models for generalist robots typically requires large-scale real-world robot data, which is expensive and time-consuming to collect. The ineff…
Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots
Wei Cui, Haoyu Wang, Wenkang Qin +19
Humanoid robot technology is advancing rapidly, with manufacturers introducing diverse heterogeneous visual perception modules tailored to specific scenarios. Among various percept…