Tong Liu

tongliuphysics's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 11 hours ago

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Text Generation • 2B • Updated Feb 24, 2025 • 614k • • 1.53k

updated a model 7 days ago

tongliuphysics/qwen3-4b-opd4-280

4B • Updated 7 days ago • 10

published a model 7 days ago

tongliuphysics/qwen3-4b-opd4-280

4B • Updated 7 days ago • 10

updated a model 9 days ago

tongliuphysics/qwen3-4b-opd4-200

4B • Updated 9 days ago • 18

published a model 9 days ago

tongliuphysics/qwen3-4b-opd4-200

4B • Updated 9 days ago • 18

upvoted a paper 9 days ago

On Effectiveness and Efficiency of Agentic Tool-calling and RL Training

Paper • 2606.00135 • Published 28 days ago • 1

updated a model about 1 month ago

tongliuphysics/qwen3-4b-opd1-320

4B • Updated May 23 • 3

published a model about 1 month ago

tongliuphysics/qwen3-4b-opd1-320

4B • Updated May 23 • 3

updated a model about 1 month ago

tongliuphysics/qwen3-4b-opd1-160

4B • Updated May 21 • 4

published a model about 1 month ago

tongliuphysics/qwen3-4b-opd1-160

4B • Updated May 21 • 4

liked 2 models 3 months ago

tongliuphysics/llama3b-instruct-80steps

4B • Updated Oct 15, 2025 • 3 • 1

tongliuphysics/qwen3-4b-looptool-turn1-5-binary-bs256-0701-step92

4B • Updated Jan 7 • 3 • 1

upvoted 3 papers 3 months ago

Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"?

Paper • 2311.09325 • Published Nov 15, 2023 • 1

Multimodal Pragmatic Jailbreak on Text-to-image Models

Paper • 2409.19149 • Published Sep 27, 2024 • 1

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings

Paper • 2501.06645 • Published Jan 11, 2025 • 1

liked 2 models 3 months ago

tongliuphysics/qwen3-4b-normal-n1-binary-rollout8-bs256-0201-real-step40

4B • Updated Jan 3 • 3 • 1

tongliuphysics/qwen3-4b-normal-n1-singleturn666-binary-rollout8-bs256-0401-step40

4B • Updated Jan 4 • 2 • 2

New activity in LiquidAI/LFM2.5-1.2B-Thinking 4 months ago

is it possible to publish the bfcl multiturn evaluation handler so that we could directly measure your model?

👍 1

1

#2 opened 5 months ago by

tongliuphysics

liked a model 5 months ago

LiquidAI/LFM2.5-1.2B-Thinking

Text Generation • 1B • Updated Mar 30 • 49.3k • 369

New activity in akseljoonas/ToolMind 5 months ago

Data quality

#1 opened 5 months ago by

tongliuphysics