SeedFold: Scaling Biomolecular Structure Prediction
Paper • 2512.24354 • Published • 3
AI & ML interests
Pioneering the Future of AGI and Building An Omnipotent Agentic Framework
thughost
authored a
paper 3 months ago
thughost
authored a
paper about 1 year ago
thughost
authored 5
papers over 1 year ago
MARS: Unleashing the Power of Variance Reduction for Training Large Models
Paper • 2411.10438 • Published • 13
DPLM-2: A Multimodal Diffusion Protein Language Model
Paper • 2410.13782 • Published • 22
General Preference Modeling with Preference Representations for Aligning Language Models
Paper • 2410.02197 • Published • 9
LLaVA-Critic: Learning to Evaluate Multimodal Models
Paper • 2410.02712 • Published • 37
ProteinBench: A Holistic Evaluation of Protein Foundation Models
Paper • 2409.06744 • Published • 8
Post
763
We've open-sourced the code and models for Self-Play Preference Optimization (SPPO)! 🚀🚀🚀
🤗paper: Self-Play Preference Optimization for Language Model Alignment (2405.00675)
⭐ code: https://github.com/uclaml/SPPO
🤗models: UCLA-AGI/sppo-6635fdd844f2b2e4a94d0b9a
🤗paper: Self-Play Preference Optimization for Language Model Alignment (2405.00675)
⭐ code: https://github.com/uclaml/SPPO
🤗models: UCLA-AGI/sppo-6635fdd844f2b2e4a94d0b9a
thughost
authored 7
papers almost 2 years ago
DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
Paper • 2403.13829 • Published
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
Paper • 2305.08359 • Published
Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
Paper • 2311.14222 • Published
How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
Paper • 2310.08391 • Published
Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
Paper • 2310.00968 • Published
Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
Paper • 2310.01380 • Published
Self-Play Preference Optimization for Language Model Alignment
Paper • 2405.00675 • Published • 28
Post
- 45 replies
thughost
authored 4
papers about 2 years ago
Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation
Paper • 2402.10210 • Published • 35
Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance
Paper • 2402.08680 • Published • 1
TrustLLM: Trustworthiness in Large Language Models
Paper • 2401.05561 • Published • 69
Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
Paper • 2311.04205 • Published • 5