5 papers
Tessera: Demand-Driven KV Cache Management for Retrieval-Augmented LLM Serving
Fei Fang, Chung-Hsiang Lo, Yi Liu +2
RAG and retrieval-based agent memory both inject retrieved content into LLM prompts, as document chunks and recalled memory records, respectively. The same content can recur across…
When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
Chung-Hsiang Lo, Lu Li, Diji Yang +4
In the LLM era, many symbolic and structured problems are presented to models through 1D text serialization. Yet some such problems are natively two-dimensional: their relevant rel…
GraphGhost: Tracing Structures Behind Large Language Models
Xinnan Dai, Xianxuan Long, Chung-Hsiang Lo +4
Large Language Models (LLMs) exhibit strong reasoning capabilities on structured tasks, yet the internal mechanisms underlying such behaviors remain poorly understood. Existing int…
Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
Xinnan Dai, Chung-Hsiang Lo, Kai Guo +3
Transformer-based LLMs demonstrate strong performance on graph reasoning tasks, yet their internal mechanisms remain underexplored. To uncover these reasoning process mechanisms in…
GenIR: Generative Visual Feedback for Mental Image Retrieval
Diji Yang, Minghao Liu, Chung-Hsiang Lo +2
Vision-language models (VLMs) have shown strong performance on text-to-image retrieval benchmarks. However, bridging this success to real-world applications remains a challenge. In…