collaborators

14 papers

cs.AI2026

The Model Knows Your Project, Not You: Measuring Recognition in LLMs with NameRank

Bojie Li, Noah Shi

What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric co…

cs.AI2026

Interaction Scaling: Grounding the Third Axis of Test-Time Compute

Bojie Li, Noah Shi

There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal. Every…

cs.CL2026

Parametric Multimodal User Memory: Storing What Captions Cannot Carry

Bojie Li, Noah Shi

A personalized agent needs a user memory: a persistent model of who its user is. Today it is almost always text -- transcripts and captions retrieved by similarity. This serves the…

cs.LG2026

RLVP: Penalize the Path, Reward the Outcome

Bojie Li, Noah Shi

Agents acting on our behalf in the real world (e.g. placing phone calls) must learn online from costly, often irreversible interactions rather than cheap simulator steps. Two thing…

cs.NI2026

OneBarrier: What a Network Must Provide for Transparent Fault Tolerance to Be Free

Bojie Li

Transparent fault tolerance -- making an unmodified server binary survive crashes -- has been pursued for four decades without reaching production. Every attempt paid three costs o…

cs.DC2026

Fine-Grained Computation Offload for Off-the-Shelf Servers in Tens of Lines

Bojie Li

Hardware accelerators now sit on the critical path of online serving. GPUs, FPGAs, and increasingly remote services such as hardware security modules, post-quantum KEMs, and infere…