arxiv:2606.23525
Tianjian Li
dogtooth
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation authored a paper 1 day ago
Many-Tier Instruction Hierarchy in LLM Agents authored a paper 1 day ago
ThoughtTrace: Understanding User Thoughts in Real-World LLM InteractionsOrganizations
models 38
dogtooth/open-lm-3b-201305-midtrain-stage2-think
Text Generation • 3B • Updated • 6
dogtooth/open-lm-3b-201305-midtrain
Text Generation • 3B • Updated • 4
dogtooth/open-lm-3b-201305-midtrain-stage1-sft
Text Generation • 3B • Updated • 3
dogtooth/open-lm-3b-202407-stage2-think
3B • Updated • 53
dogtooth/open-lm-3b-202101-stage2-think
3B • Updated • 25
dogtooth/open-lm-3b-201901-stage2-think
3B • Updated • 24
dogtooth/open-lm-3b-201701-stage2-think
3B • Updated • 24
dogtooth/open-lm-3b-201501-stage2-think
3B • Updated • 23
dogtooth/open-lm-3b-202301-stage2-think
3B • Updated • 25
dogtooth/open-lm-3b-201901-stage1-sft
Text Generation • 3B • Updated • 75
datasets 46
dogtooth/reasoning_state_rl
Viewer • Updated • 262k • 9
dogtooth/rc-annotated-sft
Viewer • Updated • 1.49k • 7
dogtooth/polaris_filtered_removed_all_correct
Viewer • Updated • 38.1k • 3
dogtooth/polaris_filtered_less_than_half_correct
Viewer • Updated • 13.8k • 2
dogtooth/llm_tool_self_context_management_sft
Viewer • Updated • 12.4k • 7
dogtooth/tool_call_truncated_synthesized_traj
Viewer • Updated • 4.54k • 9
dogtooth/tool_verify_truncated
Viewer • Updated • 2.85k • 10
dogtooth/math_training_24k
Viewer • Updated • 23.9k • 5
dogtooth/Big-Math-RL-Verified
Viewer • Updated • 1.52M • 77
dogtooth/default_project_dev_test
Viewer • Updated • 4k • 8