collaborators

6 papers

cs.LG2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…