STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Paper • 2609.38169 • Published • 131
Павел Попов
Chngupta
AI & ML interests
diffusion models, mechanistic interpretability, transfer learning, natural language understanding
Recent Activity
updated a model 6 days ago
Chngupta/thesis-multitask-2023 published a model 6 days ago
Chngupta/thesis-multitask-2023 upvoted a paper 6 days ago
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State QuantizationOrganizations
None yet
upvoted 4
papers 6 days ago
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Paper • 2610.07557 • Published • 75
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Paper • 2610.08215 • Published • 154
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
Paper • 2610.06100 • Published • 141