ttlynne/colar-checkpoints
Updated
yuelingtang
ttlynne
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
SeePhys Pro: Diagnosing Modality Transfer and Blind-Training Effects in Multimodal RLVR for Physics Reasoning published a model 1 day ago
ttlynne/colar-checkpoints updated a dataset 7 days ago
ttlynne/PhysReason_full_embeddingOrganizations
None yet
ttlynne/reward_canny_base
Updated
ttlynne/colar_checkpoints_last_checkpoint
Updated
ttlynne/colar_checkpoints
Updated
ttlynne/qwen3vl-4b-grpo-merged-250
5B • Updated • 3
ttlynne/qwen3vl-4b-grpo-merged-200
5B • Updated • 1
ttlynne/qwen3vl-4b-grpo-merged-50
5B • Updated • 3
ttlynne/qwen3vl-4b-gspo-merged-150
5B • Updated • 1
ttlynne/qwen3vl-4b-gspo-merged-200
5B • Updated • 1
ttlynne/qwen3vl-4b-gspo-merged-250
5B • Updated • 3
ttlynne/qwen3vl-4b-gspo-merged
Reinforcement Learning • Updated • 5