Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Paper • 2307.15217 • Published • 39
Mehul Damani PRO
mehuldamani
AI & ML interests
Reinforcement Learning, Large Language Models
Recent Activity
updated a model about 14 hours ago
mehuldamani/sft-qwen-hmaze-v2 published a model about 14 hours ago
mehuldamani/sft-qwen-hmaze-v2 updated a model about 23 hours ago
mehuldamani/sft-qwen-hmaze-v1Organizations
None yet
authored 4
papers 8 months ago
Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
Paper • 2507.16806 • Published • 7
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Paper • 2410.04707 • Published
The Surprising Effectiveness of Test-Time Training for Abstract Reasoning
Paper • 2411.07279 • Published • 4