10 papers
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents
Dhaval C. Patel, Kaoutar El Maghraoui, Shuxin Lin +58
Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated d…
HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
Xiaoquan Sun, Ruijian Zhang, Chen Cao +12
World Action Models (WAMs) have emerged as a new powerful paradigm for embodied intelligence, learning action-relevant visual dynamics that significantly enhance generalization and…
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Yihang Wu, Yihang Sun, Shaofeng Zhang +4
Transformer-based models have advanced feedforward novel view synthesis (NVS). Current architectures such as GS-LRM and LVSM mix semantic information (e.g., RGB) and spatial inform…
STAGE: Tackling Semantic Drift in Multimodal Federated Graph Learning
Zekai Chen, Xun Wu, Xunkai Li +3
Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. As graph data increasingly contain multimodal node attributes such as text and…
Useful Memories Become Faulty When Continuously Updated by LLMs
Dylan Zhang, Yanshan Lin, Zhengkun Wu +4
Learning from past experience benefits from two complementary forms of memory: episodic traces -- raw trajectories of what happened -- and consolidated abstractions distilled acros…
EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
Xueyang Zhou, Yihan Sun, Xijie Gong +4
Embodied AI research is increasingly moving beyond single-task, single-environment policy learning toward multi-task, multi-scene, and multi-model settings. This shift substantiall…
PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools
Yusheng Li, Tianjun Feng, Yunfeng Chen +6
LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critic…
AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models
Xiaoquan Sun, Zetian Xu, Chen Cao +9
Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be impr…
Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
Xiaosong Jia, Yihang Sun, Junqi You +5
Feedforward models for novel view synthesis (NVS) have recently advanced by transformer-based methods like LVSM, using attention among all input and target views. In this work, we…
Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructions
Cunxin Fan, Xiaosong Jia, Yihang Sun +8
The rise of foundation models paves the way for generalist robot policies in the physical world. Existing methods relying on text-only instructions often struggle to generalize to…