Rishabh Tiwari

The Art of Scaling Reinforcement Learning Compute for LLMs

SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching

Let's (not) just put things in Context: Test-time Training for Long-context LLMs

ACTS: Adaptive Control for Test-time Scaling

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache