Lei Li
@_TobiasLee
Ph.D. student@HKUNLP. Previously @PKU1898 COYG @Arsenal opinions are my own.
Thrilled to announce our MiMo-VL series hit 100K downloads on HuggingFace last month! 🚀🚀 Incredible to see the community's enthusiasm for our VLMs. More exciting updates coming soon! 😜 huggingface.co/XiaomiMiMo/MiM…
🧵 Introducing TimeScope, an open-source benchmark rigorously evaluating the true “temporal context window” of video-language models on videos ranging from 1 minute to 8 hours. #AI #MachineLearning
Tried it with Claude Code and found it much faster & cheaper than K2. My first choice for vibe coding now.
>>> Qwen3-Coder is here! ✅ We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves…
Bye Qwen3-235B-A22B, hello Qwen3-235B-A22B-2507! After talking with the community and thinking it through, we decided to stop using hybrid thinking mode. Instead, we’ll train Instruct and Thinking models separately so we can get the best quality possible. Today, we’re releasing…
Introducing ColQwen-Omni, a 3B omnimodal retriever that extends the ColPali concept of multimodal retrieval with late interaction to audio chunks and short videos, with no performance degradation on visual document retrieval wrt our best models! (1/N)
This is my lecture from 2 months ago at @Cornell “How do I increase my output?” One natural answer is "I will just work a few more hours." Working longer can help, but eventually you hit a physical limit. A better question is, “How do I increase my output without increasing…
Huan and I are looking for a postdoc to join us on agent research (broadly defined: planning, reasoning, safety, memory, continual learning, etc.). If you have a strong record in this space, drop us an email with CV! Retweet appreciated.
🚨 Postdoc Hiring: I am looking for a postdoc to work on rigorously evaluating and advancing the capabilities and safety of computer-use agents (CUAs), co-advised with @ysu_nlp @osunlp. We welcome strong applicants with experience in CUAs, long-horizon reasoning/planning,…
What happend after Dream 7B? First, Dream-Coder 7B: A fully open diffusion LLM for code delivering strong performance, trained exclusively on public data. Plus, DreamOn cracks the variable-length generation problem! It enables code infilling that goes beyond a fixed canvas.
Check Dream-Coder 7B, a new member of the Dream Family and the most powerful open Coder DLM!!
🚀 Thrilled to announce Dream-Coder 7B — the most powerful open diffusion code LLM to date.
We present DreamOn: a simple yet effective method for variable-length generation in diffusion language models. Our approach boosts code infilling performance significantly and even catches up with oracle results.
Stop by to discuss with Yiheng about Aguvis and CUA Agents!!
Attending #ICML2025 🇨🇦 this week! Will be presenting Aguvis (arxiv.org/abs/2412.04454) on July 15 at 11am, and joining Computer Use Agent Workshop @workshopcua on July 19. If you’re into digital agent research, especially around computer/browser use, let’s grab a coffee!
method #2 to prompt a breakthrough: run those "what if i just..." / "will it break if ..." experiments, purely out of curiosity. the results may surprise you, and give you the clue you need
why does the breakthrough always happen 0-1 days before the deadline
great work, always like controlled (even just toy) experiments. I'm afraid we can't have OOD generalization in current overparameterization ML system. I’ve recently grown fond of pattern/concept narratives. In fact, I don’t believe that data-driven neural networks are capable of…
Our paper aims to answer two questions: 1. What's the difference between prediction and world models? 2. Are there straightforward metrics that can test this distinction? Our paper is about AI. But it's helpful to go back 400 years to answer these questions.
⚡️⚡️
📢 We are open sourcing ⚡Reka Flash 3.1⚡ and 🗜️Reka Quant🗜️. Reka Flash 3.1 is a much improved version of Reka Flash 3 that stands out on coding due to significant advances in our RL stack. 👩💻👨💻 Reka Quant is our state-of-the-art quantization technology. It achieves…
use our state-of-the-art research agent via api or try here app.reka.ai/research
🚀 Meet Reka Research––agentic AI that 🤔 thinks → 🔎 searches → ✏️ cites across the open web and private docs to answer your questions. 🥇 State-of-the-art performance, available now via our API and Playground!
Introducing FlexOlmo, a new paradigm for language model training that enables the co-development of AI through data collaboration. 🧵
🚀 Meet Reka Research––agentic AI that 🤔 thinks → 🔎 searches → ✏️ cites across the open web and private docs to answer your questions. 🥇 State-of-the-art performance, available now via our API and Playground!
SmolVLM has been accepted to @COLM_conf 2025 🥳! See you in Montreal!
Introducing the smollest VLMs yet! 🤏 SmolVLM (256M & 500M) runs on <1GB GPU memory. Fine-tune it on your laptop and run it on your toaster. 🚀 Even the 256M model outperforms our Idefics 80B (Aug '23). How small can we go? 👀
Excited to introduce Reka Vision, an agentic visual understanding and search platform. Transform your unstructured multimodal data into insights and actions.
In ACM MM 2025, we introduced "Multi-Agent System for Comprehensive Soccer Understanding" with @WeidiXie ⚽️AI with external knowledge to analyze on/off-field dynamics! 🧐 📄: arxiv.org/abs/2505.03735 🌐: jyrao.github.io/SoccerAgent/ See details below! #AI4Sports #MultiAgent #ACMMM25