arxiv:2509.02534
Tianjian Li
dogtooth
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Many-Tier Instruction Hierarchy in LLM Agents updated a model 8 days ago
dogtooth/open-lm-3b-202407-sft-nontemporal published a model 8 days ago
dogtooth/open-lm-3b-202407-sft-nontemporalOrganizations
models 21
dogtooth/open-lm-3b-202407-sft-nontemporal
Feature Extraction • 3B • Updated • 70
dogtooth/open-lm-3b-202301-sft-nontemporal
Feature Extraction • 3B • Updated • 62
dogtooth/open-lm-3b-202101-sft-nontemporal
Feature Extraction • 3B • Updated • 61
dogtooth/open-lm-3b-201901-sft-nontemporal
Feature Extraction • 3B • Updated • 87
dogtooth/Qwen3-4B-Instruct-2507-SFT
4B • Updated • 1
dogtooth/open-lm-3b-202407
Text Generation • 3B • Updated • 53
dogtooth/open-lm-3b-202301
Text Generation • 3B • Updated • 51
dogtooth/open-lm-3b-202101
Text Generation • 3B • Updated • 49
dogtooth/open-lm-3b-201901
Text Generation • 3B • Updated • 57
dogtooth/open-lm-3b-201701
Text Generation • 3B • Updated • 52
datasets 46
dogtooth/reasoning_state_rl
Viewer • Updated • 262k • 15
dogtooth/rc-annotated-sft
Viewer • Updated • 1.49k • 18
dogtooth/polaris_filtered_removed_all_correct
Viewer • Updated • 38.1k • 8
dogtooth/polaris_filtered_less_than_half_correct
Viewer • Updated • 13.8k • 8
dogtooth/llm_tool_self_context_management_sft
Viewer • Updated • 12.4k • 24
dogtooth/tool_call_truncated_synthesized_traj
Viewer • Updated • 4.54k • 7
dogtooth/tool_verify_truncated
Viewer • Updated • 2.85k • 7
dogtooth/math_training_24k
Viewer • Updated • 23.9k • 8
dogtooth/Big-Math-RL-Verified
Viewer • Updated • 1.52M • 32
dogtooth/default_project_dev_test
Viewer • Updated • 4k • 17