8 papers
Self-Evolving Code-with-Image Reasoning
Tianze Yang, Liang Wu, Ruitong Sun +6
Multimodal models increasingly reach for tools when solving visual tasks (crop, zoom, rotate, brighten), a paradigm known as thinking-with-images. The central challenge is one of p…
SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding
Jiamu Zhang, Liang Wu, Kelly Wan +2
Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns. Their inference memory is then…
Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
Guanghui Min, Liang Wu, Mayank Darbari +2
Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood. In this preliminary empirical study, we show that…
Field Aware Agent Skill Retrieval
Paimon Goulart, Liang Wu, Kelly Wan +2
As lifelong learning agents accumulate lifelong growing skill banks, retrieving the correct skill becomes an increasingly important bottleneck. Most current skill retrieval methods…
WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware
Jiamu Zhang, Liang Wu, Mayank Darbari +1
Modern Mixture-of-Experts (MoE) models place most of their parameters in expert layers, yet only a small fraction of those experts are used for any token. The unused weights must s…
Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G
Liang Wu, Kelly Wan, Mayank Darbari +1
The proliferation of emerging applications, such as autonomous driving and immersive experiences, demands cellular networks that are not only faster, but fundamentally more resilie…