2 citations · 2 across the 14 of their papers we have counts for
18 papers
Exploring the Limits of Combinatorial Generalization in Embodied Manipulation
Xupeng Zhang, Yantai Yang, Chang Guo +2
In embodied manipulation, Vision Language Action (VLA) models can execute atomic skills, but long-horizon manipulation requires recombining these skills without demonstrations for…
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Chang Guo, Yukun Xie, Bohan Tan +6
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker than these numbers suggest. We trace this illusion to a struct…
Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models
Zhaokai Yin, Zhipeng Zhang
Vision-Language-Action (VLA) models excel in robotic manipulation but suffer catastrophic performance drops when canonical instructions are simply paraphrased. Although this brittl…
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
Yan Wang, Xiulong Yuan, Kaiming Yang +16
Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost ope…
GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environments
Jiawei Zhang, Yiming Yan, Chao Liang +8
Training embodied agents in the real world requires skilled operators and expensive hardware. Simulation environments offer a compelling alternative by enabling large-scale, cost-e…
YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition
PSBC LLM Team, Huawei LLM Team, Ruihan Long +56
Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates inf…
Silent Collapse in Recursive Learning Systems
Zhipeng Zhang
Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-…
Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
Zixing Lei, Changxing Liu, Yichen Xiong +5
Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burden of extended closed-loop planning and…
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
Huashuo Lei, Wenxuan Song, Huarui Zhang +10
Memory is a critical component of robotic intelligence, as robots must rely on past observations and actions to accomplish long-horizon tasks in partially observable environments.…
Accelerating Compound LLM Training Workloads with Maestro
Xiulong Yuan, Hongqing Chen, Jiaxuan Peng +16
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differin…
Beyond Isolation: A Unified Benchmark for General-Purpose Navigation
Samson Sun, Tianyi Yang, Tengyue Wang +6
The pursuit of general-purpose embodied agents is hindered by fragmented evaluation protocols that isolate navigation skills and fixate on specific robot morphologies, failing to r…
QVLA: Not All Channels Are Equal in Vision-Language-Action Model's Quantization
Yuhao Xu, Yantai Yang, Zhenyang Fan +4
The advent of Vision-Language-Action (VLA) models represents a significant leap for embodied intelligence, yet their immense computational demands critically hinder deployment on r…
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
Shuai Yuan, Yantai Yang, Xiaotian Yang +4
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offlin…
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Yunhong Lu, Yanhong Zeng, Haobo Li +9
Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attenti…
FlowDrive: Energy Flow Field for End-to-End Autonomous Driving
Hao Jiang, Zhipeng Zhang, Yu Gao +11
Recent advances in end-to-end autonomous driving leverage multi-view images to construct BEV representations for motion planning. In motion planning, autonomous vehicles need consi…
ReasoningTrack: Chain-of-Thought Reasoning for Long-term Vision-Language Tracking
Xiao Wang, Liye Jin, Xufeng Lou +4
Vision-language tracking has received increasing attention in recent years, as textual information can effectively address the inflexibility and inaccuracy associated with specifyi…
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
Yantai Yang, Yuhao Wang, Zichen Wen +5
Vision-Language-Action (VLA) models, particularly diffusion-based architectures, demonstrate transformative potential for embodied intelligence but are severely hampered by high co…
Orion-14B: Open-source Multilingual Large Language Models
Du Chen, Yi Huang, Xiaopu Li +7
In this study, we introduce Orion-14B, a collection of multilingual large language models with 14 billion parameters. We utilize a data scheduling approach to train a foundational…