Jia-Wei Han

Sparse autoencoders unlock a shared, interpretable coordinate system for matching symbols across diverse AI systems, outperforming dense baselines by up to 45 points.

A novel two-axis framework unifies the study of multimodal agent memory, revealing distinct tiers of memory adaptation from static reuse to self-evolving policies.

Cracking LLM ideation requires more than high sampling temperatures: reinforcement learning over cognitive creativity axes expands scientific exploration diversity by 28% while boosting proposal originality by 66 percentage points.

Across three models, two reasoning regimes, and two domains, four findings hold without per-turn reasoning: displaying accurate state is unreliable, an unverified ledger the agent writes itself beats an accurate checklist it is shown, directives help in proportion to the model's obedience, and enforcement needs no obedience but is bounded by the correctness of its state.

Complex scoring algorithms for KV cache compression are largely unnecessary: protecting the initial prompt and dropping reasoning tokens completely at random matches state-of-the-art accuracy with up to 43% higher serving throughput.

Rollout design in LLM reinforcement learning is more than just sampling trajectories – it's a modular pipeline you can optimize for reliability, coverage, and cost.