9 papers
ChunkAct: Action Chunking for Agentic Robotics
Bingxin Xu, Wenrui Bao, Xinxin Liu +3
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidanc…
SABRE: Scalable and Automated Benchmarking of VLMs under Stress
Zixuan Lan, Luzhe Sun, Matthew R. Walter +1
Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisf…
Flow-based Policy Adaptation without Policy Updates
Luzhe Sun, Jingtian Ji, Haoran Chen +2
Foundation models and other policies trained on large and diverse datasets can endow robots with semantic and task knowledge that would be difficult to acquire from task-specific d…
HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models
Jawad Hossain, Xiangyu Guo, Jiawei Zhou +1
Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps and to recover from early erro…
Robotic Manipulation is Vision-to-Geometry Mapping: Vision-Geometry Backbones over Language and Video Models
Zijian Song, Qichang Li, Jiawei Zhou +4
At its core, robotic manipulation is a problem of vision-to-geometry mapping (). Physical actions are fundamentally defined by geometric properties like 3D posi…
HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token
Sai Akhil Kogilathota, Sripadha Vallabha E G, Luzhe Sun +1
Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically op…
Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
Haoyan Yang, Mario Xerri, Solha Park +4
As large language models (LLMs) continue to advance, improving them solely through human supervision is becoming increasingly costly and limited in scalability. As models approach…
From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration
Mingyang Song, Xiaoye Qu, Jiawei Zhou +1
Large Vision-Language Models (LVLMs) have achieved significant progress in combining visual comprehension with language generation. Despite this success, the training data of LVLMs…
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models
Mingyang Song, Zhaochen Su, Xiaoye Qu +2
Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since…