Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective
Paper
•
2505.19815
•
Published
•
36
InternLM
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
internlm's activity
zsytony
authored
a
paper
11 days ago
myownskyW7
authored
7
papers
17 days ago
MMDetection: Open MMLab Detection Toolbox and Benchmark
Paper
•
1906.07155
•
Published
VideoRoPE: What Makes for Good Video Rotary Position Embedding?
Paper
•
2502.05173
•
Published
•
65
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Paper
•
2502.08590
•
Published
•
44
RelightVid: Temporal-Consistent Diffusion Model for Video Relighting
Paper
•
2501.16330
•
Published
•
2
DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies
Paper
•
2503.14324
•
Published
•
2
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning
Paper
•
2505.03318
•
Published
•
92
Visual Agentic Reinforcement Fine-Tuning
Paper
•
2505.14246
•
Published
•
31
Update README.md
#5 opened 18 days ago
by
yuhangzang
clefourrier
posted
an
update
19 days ago
Post
611
Always surprised that so few people actually read the FineTasks blog, on
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
-
- 2 replies
QipengGuo
authored
a
paper
about 2 months ago
myownskyW7
authored
a
paper
about 2 months ago
pppppM
authored
a
paper
2 months ago
ZwwWayne
authored
a
paper
2 months ago
Add Hugging Face paper link to dataset card
#2 opened 4 months ago
by
nielsr
Missing FAIL_TO_PASS and PASS_TO_PASS Fields
1
#3 opened 3 months ago
by
zengliangcs
Post
3502
🔥MedAgentBench Amazing Work🚀
Just explored #MedAgentBench from @Yale researchers and it's mind-blowing! They've created a cutting-edge benchmark that finally exposes the true capabilities of LLMs in complex medical reasoning.
⚡ Key discoveries:
DeepSeek R1 & OpenAI O3 dominate clinical reasoning tasks
Agent-based frameworks deliver exceptional performance-cost balance
Open-source alternatives are closing the gap at fraction of the cost
This work shatters previous benchmarks that failed to challenge today's advanced models.
The future of medical AI is here: https://github.com/gersteinlab/medagents-benchmark
#MedicalAI #MachineLearning #AIinHealthcare 🔥
Just explored #MedAgentBench from @Yale researchers and it's mind-blowing! They've created a cutting-edge benchmark that finally exposes the true capabilities of LLMs in complex medical reasoning.
⚡ Key discoveries:
DeepSeek R1 & OpenAI O3 dominate clinical reasoning tasks
Agent-based frameworks deliver exceptional performance-cost balance
Open-source alternatives are closing the gap at fraction of the cost
This work shatters previous benchmarks that failed to challenge today's advanced models.
The future of medical AI is here: https://github.com/gersteinlab/medagents-benchmark
#MedicalAI #MachineLearning #AIinHealthcare 🔥
x54-729
updated
3
models
3 months ago