Lingpeng Kong
113 posts
Lingpeng Kong
@ikekong
Assistant Professor @ The University of Hong Kong, Previously Research Scientist @ DeepMind
Hong Kong Katılım Şubat 2010
301 Takip Edilen1.1K Takipçiler
Lingpeng Kong retweetledi
Agents are doing real work, but existing benchmarks still test them in isolation.
Today we’re releasing Claw-Eval 🦞: an open-source, transparent evaluation framework for AI agents.
We feature 104 tasks spanning daily assistants, Office QA, deep finance research, and terminal usage.
We test completion, robustness, and safety across real and mock services with configurable error injection.
Fully traceable and human-verified.
First leaderboard results: Claude Opus 4.6 @AnthropicAI tops pass rate (68.3%), but Gemini 3.1 @GeminiApp Pro edges it on avg score (0.764 vs 0.759).
Agents have a long way to go.🤨
Check it out: claw-eval.github.io
@steipete @openclaw
English
Lingpeng Kong retweetledi
Introducing proxy compression for end-to-end language modeling: train on compressed (e.g., tokenized) data for efficiency, but run inference entirely on raw bytes without a tokenizer. No architectural changes required. At scale, proxy-trained byte models match or surpass tokenizer baselines at 7B and 14B.
📄 Paper: arxiv.org/abs/2602.04289
💻 Code: github.com/LZhengisme/pro…
[1/9]
🧵👇
English
🚀 Introducing Dream-VL & Dream-VLA!
We’re proving that dLLMs have an amazing advantage in building VLA models.
The result is stunning performance:
🏆 97.2% on LIBERO
⚡ 27x speedup vs AR models
🔥 Beats OpenVLA & $\pi_0$
✅ Fully Open Source
Blog: hkunlp.github.io/blog/2025/drea…
Jiacheng Ye@JiachengYe15
🚀Building on the success of Dream 7B, we introduce Dream-VL and Dream-VLA, open VL and VLA models that fully unlock discrete diffusion’s advantages in long-horizon planning, bidirectional reasoning, and parallel action generation for multimodal tasks.
English
We use latent continuous thoughts for retrieval optimized via downstream NTP loss, unified under one LLM backbone. Since representations are shared, documents can be precomputed—eliminating 2-stage RAG. We match raw text performance but with a much shorter context budget. 📉🚀
Jie He@Jiehenlp
Happy to introduce my internship work at @Apple . We introduce CLaRa: Continuous Latent Reasoning, an end-to-end training framework that jointly trains retrieval and generation ! 🧠📦 🔗 arxiv.org/pdf/2511.18659… #RAG #LLMs #Retrieval #Reasoning #AI
English
Smarter TTS by Xueliang! See everyone in this year NeurIPS!
Xueliang Zhao@xlzhao_hku
🚀 Thrilled to share our #NeurIPS2025 paper DynaAct: Large Language Model Reasoning with Dynamic Action Spaces A new test-time scaling view — optimizing the action space itself, while providing a general MCTS acceleration framework for reasoning. 💻 github.com/zhaoxlpku/Dyna…
English
Lingpeng Kong retweetledi
This is super cool. I strongly believe that the flexibility of dLLMs during generation will enable new features for agent use.
Guido Appenzeller@appenz
Diffusion LLM + Agents are 🔥 This is @_inception_ai's Diffusion LLM with @huggingface SmolAgents: - Planning tool use - Executing 20 web searches and parsing results - Synthesizing the data All in 3.5 seconds. With 10 searches it took only 1.6 seconds. Source on GitHub below.
English
Lingpeng Kong retweetledi
We will have a guest talk from Cai Zhou. He is a second-year PhD in MIT EECS. "Continuous modeling in diffusion language models: HDLM and CCDD
". All are welcome to join via the following link.
hku.zoom.us/j/91579619608?…
English
Lingpeng Kong retweetledi
DeepSeek-OCR: Exploring the boundaries of visual-text compression.
Ambitious! They might use 10X (near-lossless) compressed vision tokens to replace the KV cache of dialog histories.
github.com/deepseek-ai/De…
English
Lingpeng Kong retweetledi
The full Dream-Coder pipeline is now open-sourced—covering data prep, training, and evaluation. Check it out! github.com/DreamLM/Dream-…
Zhihui Xie@_zhihuixie
🚀 Thrilled to announce Dream-Coder 7B — the most powerful open diffusion code LLM to date.
English
Saw the paper like a month ago. Now with the demo it only gets cooler :p
Yanzhe Zhang@StevenyzZhang
Introducing Generative Interfaces - a new paradigm beyond chatbots. We generate interfaces on the fly to better facilitate LLM interaction, so no more passive reading of long text blocks. Adaptive and Interactive: creates the form that best adapts to your goals and needs!
English
Lingpeng Kong retweetledi
🌟 Thrilled to share our paper, "TreeSynth," has been accepted for a Spotlight presentation at #NeurIPS2025!
🤔 Struggling with repetition & space collapse in data synthesis? Our work introduces 🌳TreeSynth, a novel framework using tree-guided partitioning to generate large-scale, diverse datasets from scratch.
🏆 Models trained on TreeSynth data consistently outperform those trained on human-crafted datasets and other synthetic methods.
See you all at NeurIPS!
🔗 Paper: arxiv.org/abs/2503.17195
💻 Code: github.com/cpa2001/TreeSy…
English
Lingpeng Kong retweetledi
Jinjie Ni @NiJinjie from NUS will be giving a talk titled "Diffusion Language Models are Super Data Learners" at Friday Aug 22 11am HKT. link to talk: hku.zoom.us/j/94293996114?…
English
Lingpeng Kong retweetledi
🚀 MiMo‑VL 2508 is live! Same size, much smarter.
We’ve upgraded performance, thinking control, and overall user experience.
📈 Benchmark gains across image + video: MMMU 70.6, VideoMME 70.8.
Consistent improvements across the board.
🤖 Thinking Control: toggle reasoning with `no_think`.
On (default): full reasoning visible;
Off: direct answers, no reasoning ⚡⚡;
❤️ Real‑world user experience: our VLM Arena rating improved from 1093.9 → 1131.2 (+37.3).
More capable, flexible, and reliable in everyday tasks.
Feedback welcome.
🤗 RL Version: huggingface.co/XiaomiMiMo/MiM…
🤗 SFT Version: huggingface.co/XiaomiMiMo/MiM…
#XiaomiMiMo
English
Lingpeng Kong retweetledi
Xinyu Yang from CMU will be giving a talk titled "Multiverse: Your Language Models Secretly
Decide How to Parallelize and Merge Generation" at Friday July 25 11am HKT (Thursday July 24 8pm PDT). Link to talk: hku.zoom.us/j/92651812689?…
English
Lingpeng Kong retweetledi
📢 Update: Announcing Dream's next-phase development.
- Dream-Coder 7B: A fully open diffusion LLM for code delivering strong performance, trained exclusively on public data.
- DreamOn: targeting the variable-length generation problem in dLLM!
English
Lingpeng Kong retweetledi
🚀 Thrilled to announce Dream-Coder 7B — the most powerful open diffusion code LLM to date.
English
Lingpeng Kong retweetledi
Please check out our blogs here.
Dream-Coder 7B: hkunlp.github.io/blog/2025/drea…
DreamOn: hkunlp.github.io/blog/2025/drea…
English
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.
GIF
GIF
GIF
English