SciTrek Collection Models for the paper of "Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles" • 6 items • Updated 8 days ago
oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 8 days ago • 55
oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 8 days ago • 55
oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 12 days ago • 385
oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 12 days ago • 385
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 16 days ago • 257
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507 Text Generation • 4B • Updated 16 days ago • 257
oaimli/longtune_scitrek_grounding_reinforcement_gemma_0 Image-Text-to-Text • 4B • Updated 19 days ago • 43
ProxyCoT Collection Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 19 days ago
ProxyCoT Collection Models for Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning (ACL 2026) • 18 items • Updated 19 days ago