6 papers
HindSearch: Trajectory-Level Hindsight Critique for Search-Augmented Reinforcement Learning
Haowei Liu, Jiamian Wang, Hsin-Tai Wu +2
Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed. We introduce Hin…
Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving
Meibo Hu, Jiamian Wang, Pichao Wang +1
Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation in…
DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents
Jiamian Wang, Ruiyi Zhang, Tong Yu +5
Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples serve as the training envir…
Visual Self-Refinement for Autoregressive Models
Jiamian Wang, Ziqi Zhou, Chaithanya Kumar Mummadi +5
Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequen…
X-CoT: Explainable Text-to-Video Retrieval via LLM-based Chain-of-Thought Reasoning
Prasanna Reddy Pulakurthi, Jiamian Wang, Majid Rabbani +3
Prevalent text-to-video retrieval systems mainly adopt embedding models for feature extraction and compute cosine similarities for ranking. However, this design presents two limita…
Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
Jiamian Wang, Zongliang Wu, Yulun Zhang +3
Existing reconstruction models in snapshot compressive imaging systems (SCI) are trained with a single well-calibrated hardware instance, making their performance vulnerable to har…