-
lixiaochuan2020/qwen3-1.7b-midtrain-baseline
Text Generation • 2B • Updated • 53 -
lixiaochuan2020/qwen3-1.7b-midtrain-local-kv-per-document
Text Generation • 2B • Updated • 52 -
lixiaochuan2020/qwen3-1.7b-rl-baseline
Text Generation • 2B • Updated • 37 -
lixiaochuan2020/qwen3-1.7b-rl-local-kv-per-document
Text Generation • 2B • Updated • 37
Xiaochuan Li PRO
lixiaochuan2020
AI & ML interests
None yet
Recent Activity
updated a model about 11 hours ago
lixiaochuan2020/scottyrl-a3-p5_textcraft_grpo published a model about 11 hours ago
lixiaochuan2020/scottyrl-a3-p5_textcraft_grpo updated a collection 3 days ago
kv-midtrainOrganizations
ACM: Agentic Context Management for Long Horizon Tasks
-
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch1
Preview • Updated • 159 -
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch2
Preview • Updated • 167 -
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b
Updated • 7.91k -
lixiaochuan2020/acm-browsecompplus-teacher-logprobs-qwen3.5-9b-epoch1
Updated • 2.09k
kv-midtrain
-
lixiaochuan2020/qwen3-1.7b-midtrain-baseline
Text Generation • 2B • Updated • 53 -
lixiaochuan2020/qwen3-1.7b-midtrain-local-kv-per-document
Text Generation • 2B • Updated • 52 -
lixiaochuan2020/qwen3-1.7b-rl-baseline
Text Generation • 2B • Updated • 37 -
lixiaochuan2020/qwen3-1.7b-rl-local-kv-per-document
Text Generation • 2B • Updated • 37
ACM: Agentic Context Management for Long Horizon Tasks
-
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch1
Preview • Updated • 159 -
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch2
Preview • Updated • 167 -
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b
Updated • 7.91k -
lixiaochuan2020/acm-browsecompplus-teacher-logprobs-qwen3.5-9b-epoch1
Updated • 2.09k
models 14
lixiaochuan2020/scottyrl-a3-p5_textcraft_grpo
Updated
lixiaochuan2020/qwen3-4b-midtrain-local-kv-per-document
Text Generation • 4B • Updated • 151
lixiaochuan2020/qwen3-4b-rl-local-kv-per-document
Text Generation • 4B • Updated • 156
lixiaochuan2020/qwen3-4b-midtrain-baseline
Text Generation • 4B • Updated • 167
lixiaochuan2020/qwen3-4b-rl-baseline
Text Generation • 4B • Updated • 167
lixiaochuan2020/qwen3-1.7b-rl-local-kv-per-document
Text Generation • 2B • Updated • 37
lixiaochuan2020/qwen3-1.7b-rl-baseline
Text Generation • 2B • Updated • 37
lixiaochuan2020/qwen3-1.7b-midtrain-local-kv-per-document
Text Generation • 2B • Updated • 52
lixiaochuan2020/qwen3-1.7b-midtrain-baseline
Text Generation • 2B • Updated • 53
lixiaochuan2020/latent-wm-160m-suite
Updated
datasets 8
lixiaochuan2020/acm-browsecompplus-teacher-logprobs-qwen3.5-9b-epoch3
Updated • 1.59k
lixiaochuan2020/acm-browsecompplus-teacher-logprobs-qwen3.5-9b-epoch2
Updated • 1.87k
lixiaochuan2020/acm-browsecompplus-teacher-logprobs-qwen3.5-9b-epoch1
Updated • 2.09k
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch2
Preview • Updated • 167
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b-epoch1
Preview • Updated • 159
lixiaochuan2020/acm-browsecompplus-train-rollouts-qwen3.5-9b
Updated • 7.91k
lixiaochuan2020/bcp_env
Viewer • Updated • 7.47k • 453
lixiaochuan2020/octothinker_decay_stage2_1Btokens
Updated • 1.12k