Xichen Zhang
4 papers · 2026–2026 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
policy optimization
(3)
credit assignment
(2)
curriculum learning
(1)
text-to-image generation
(1)
knowledge graph
(1)
vision-language model
(1)
taylor approximation
(1)
process reward model
(1)
image-to-image generation
(1)
large language model
(1)
token-level reward
(1)
search agent
(1)
semantic verification
(1)
reward calibration
(1)
reinforcement learning
(1)
reward attribution
(1)
sim-to-real transfer
(1)
Papers
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation
ACL 2026
TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization
ACL 2026
Unlocking Token Rewards via Training-Free Reward Attribution
CVPR 2026
VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis
CVPR 2026