Invited to the AAAI 2027 Senior Program Committee

ACM Multimedia 2026 logoPaper

Three papers accepted to ACM MM 2026

VertiKV, PruneVAR, and SPECTRA are accepted to ACM MM 2026 — on vertical-integrity KV-cache compression for efficient multimodal long-context inference, training-free acceleration of visual autoregressive generation, and autonomous edge–cloud GUI grounding on device, respectively.

GUI-Anything sidecar observer for long Claude Code sessionsOpen Source

GUI-Anything is open-source — a flight recorder for long Claude Code sessions

We open-sourced GUI-Anything, a sidecar Flow Observer for Claude Code that watches live session streams, visualizes explorations as timelines and flowcharts, and brings local wiki context back on demand without interrupting the coding flow.

GitHub275Project Page
DeskCraft desktop GUI agent benchmark overviewOpen Source

DeskCraft is open-source — a benchmark for desktop GUI agents

DeskCraft puts desktop GUI agents to work on real professional workflows — 538 executable tasks spanning office, design, video, audio, 3D, and multi-app software, with human-in-the-loop collaboration. Code and paper are out now.

GitHub122Paper
paper2anything — one paper PDF turned into slides, a poster, a webpage, and social-media coversOpen Source

paper2anything is open-source — turn any paper PDF into slides, a poster, a webpage, or social posts

We open-sourced paper2anything, an agent skills pack that turns an academic paper PDF into a presentation deck, conference poster, project homepage, Xiaohongshu post, or WeChat article — each generated end-to-end and ready to share.

GitHub324Project Page
Repo-Docs skill for readable, understandable project codeOpen Source

Repo-Docs is open-source — help agents and humans understand your code

We open-sourced Repo-Docs, a coding-agent skill that turns fast-changing repos into something you can actually read. It builds and keeps repo-docs/ in sync with the code—walkthroughs, concept pages, glossary, change log, and agent rules—so newcomers can trace real behavior and understand design without hunting through files or chat.

GitHub432README
Video Production Buddy AI video production studioOpen Source

Video Production Buddy — an open-source AI video production agent

We open-sourced Video Production Buddy: an AI studio that turns general-purpose agents into video production experts — guiding the brief, proposal gates, asset generation, composition, and review before committing to expensive generation runs.

GitHub583Project Page
RetentiveKV framework overviewPaper

RetentiveKV accepted to ACL 2026 Findings

RetentiveKV reformulates KV cache eviction from discrete context truncation to continuous memory evolution using entropy-driven State Space Models, achieving 5× KV cache compression and 1.5× decoding acceleration on multimodal benchmarks.

BlogPaperGitHub1小红书
Overview of the proposed ThinkRec.Paper

ThinkRec accepted to WWW 2026

ThinkRec reframes LLM-based recommendation as a reasoning problem, letting the model explicitly reason about user preferences to improve recommendation quality and user trust.

BlogPaperGitHub34
Graph2Eval knowledge-graph task generation overviewPaper

Graph2Eval accepted to CVPR 2026

Graph2Eval turns documents and web pages into a knowledge-graph task space for scalable, controllable evaluation of RAG and web agents.

BlogPaperGitHub26小红书公众号
EcoAgent workflow — cloud-side Dual-ReACT planning closes the loop with device-side execution and pre-understood observation feedback.Paper

EcoAgent accepted to AAAI 2026

EcoAgent is a closed-loop device-cloud multi-agent framework for mobile automation that matches cloud-only baselines on AndroidWorld while cutting MLLM tokens by 96% and per-step latency from 15.3s to 3.9s.

BlogPaperGitHub20
Overview of CHORD device-cloud mixed-precision quantizationPaper

CHORD accepted to ACM MM 2025

CHORD customizes a hybrid-precision on-device recommendation model for each instance, achieving personalized, resource-adaptive deployment in a single forward pass.

BlogPaper