News
Recent updates from my research, open-source work, and AMAP-ML team. I use this page as a lightweight activity log that connects papers, released code, product-facing AI systems, and hiring signals back to the broader AMAP-ML GitHub organization.
Latest AMAP-ML Updates
These items are curated from recent AMAP-ML releases and paper/project updates, with the newest and most product-relevant signals first.
- 2026.05.18 — MobilityBench accepted to KDD 2026, providing a scalable benchmark for route-planning agents in real-world mobility scenarios.
- 2026.05.12 — CoEvolve accepted to ACL 2026, training LLM agents through agent-data mutual evolution.
- 2026.05.12 — Thinking-with-Map accepted to ACL 2026 Findings, strengthening geolocalization with map-augmented reasoning.
- 2026.05.11 — DreamX-World released the 5B-Cam model and inference code for interactive world simulation.
- 2026.04.22 — DCW accepted to CVPR 2026, mitigating SNR-t bias in diffusion probabilistic models.
- 2026.04.10 — SkillClaw released an agentic evolver that turns real interaction traces into reusable skill libraries.
- 2026.04.01 — MACE-Dance accepted to SIGGRAPH 2026, decoupling motion generation and appearance synthesis for music-driven dance video.
- 2026.03.23 — Omni-WorldBench released a benchmark for interactive response capabilities of world models.
- 2026.02.06 — GPG accepted to ICLR 2026 and adopted by ByteDance’s VERL as an official reasoning RL algorithm.
- 2026.02.06 — Tree-GRPO accepted to ICLR 2026, replacing independent chain rollouts with tree-search rollouts for LLM agent reinforcement learning.
Selected GitHub Portfolio
The AMAP-ML GitHub organization is the best place to follow the full project portfolio. It organizes our work around spatial intelligence, generative intelligence, reasoning agents, world models, multimodal AI, and foundation architectures. Selected flagship releases:
Full release index: visit github.com/AMAP-ML for the complete repository list, pinned releases, project pages, and hiring notes.
2025
- USP accepted to ICCV 2025, proposing unified self-supervised pretraining for image generation and understanding. [paper] [code]
- AMAP-ML continued hiring for interns, full-time researchers, and AI engineers in LLM agents, reinforcement learning, world models, multimodal learning, spatial intelligence, and generative AI. [team]
Earlier Highlights
- VisionLLaMA accepted to ECCV 2024, a unified LLaMA-style backbone for vision tasks. [paper] [code]
- MobileVLM released, bringing real-time vision-language models to mobile devices. [paper] [code]
- YOLOv6 open-sourced, an industrial-grade real-time object detection framework. [code]
- Twins accepted to NeurIPS 2021, revisiting spatial attention design in Vision Transformers. [paper] [code]