Model checkpoints from the EMNLP 2025 paper "Improving Context Fidelity via Native Retrieval-Augmented Reasoning" by Wang et al.
Suyuchen Wang PRO
sheryc
AI & ML interests
Playing with LLMs
Recent Activity
upvoted a paper about 8 hours ago
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs liked a model about 1 month ago
Qwen/Qwen3.8-27BOrganizations
datasets 27
sheryc/UGround-V1-Data-Coordinate
Viewer • Updated • 1.23M • 316
sheryc/DROP_care
Viewer • Updated • 86.9k • 43
sheryc/ms_marco_care
Viewer • Updated • 99.3k • 44
sheryc/hotpotqa_care
Viewer • Updated • 7.74k • 27
sheryc/m2w_negative_v2
Viewer • Updated • 11.7k • 123
sheryc/LongBench-hotpotqa-with-evidence-label
Viewer • Updated • 200 • 70
sheryc/MuSiQue_care
Viewer • Updated • 22.4k • 40
sheryc/instruct-concat-100-tokenized-llama3
Viewer • Updated • 16k • 13
sheryc/instruct-concat-100-tokenized-llama1-2
Viewer • Updated • 16k • 13
sheryc/wiki40b_it_test_1k_instances_processed
Viewer • Updated • 1k • 17