“What is the answer of 1 + 1?”.Large Reasoning Models (LRMs) may generate 1500+ tokens just to answer this trivial question. Too much thinking 🤯.Can LRMs be both Faster AND Stronger?. Yes. Introducing LASER💥: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping

RT @terryyuezhuo: Training Agents without Runtime? Yes, and it works well on Offensive Cybersecurity!. Introducing Cyber-Zero, the first ap….

RT @fengyao1909: Failing on 𝐥𝐚𝐫𝐠𝐞-𝐬𝐜𝐚𝐥𝐞 𝐑𝐋 with VeRL?. ⚠️ Mixing inference backend (𝐯𝐋𝐋𝐌/𝐒𝐆𝐋𝐚𝐧𝐠) with training backends (𝐅𝐒𝐃𝐏/𝐌𝐞𝐠𝐚𝐭𝐫𝐨𝐧) 𝐬𝐞𝐜….

RT @anneouyang: KernelBench v0.1 is out, featuring:.- A guideline on analyzing the validity of results and ruling out physically impossible….

RT @_akhaliq: BANG. Dividing 3D Assets via Generative Exploded Dynamics

RT @ChujieZheng: Proud to introduce Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant RL algorithm that powe….

RT @yuntiandeng: Today I learned a student of mine from China gave up waiting for his Canadian visa after over a year without updates:. 1.….

RT @sivil_taram: 🚀 Just one week after SWE-Perf launched (the first repository-level benchmark for realistic code performance optimization)….

RT @sivil_taram: Wrapped up a SWE-Perf website redesign using Qwen3-Coder on AnyCoder (. The process was incredibly….

RT @sivil_taram: 🔥 LLMs can fix bugs, but can they make your code faster? We put them to the test on real-world repositories, and the resul….

RT @_zhihuixie: 🚀 Thrilled to announce Dream-Coder 7B — the most powerful open diffusion code  LLM to date.

RT @ikekong: What happend after Dream 7B?. First, Dream-Coder 7B: A fully open diffusion LLM for code delivering strong performance, traine….

RT @yuntiandeng: Can we build an operating system entirely powered by neural networks?. Introducing NeuralOS: towards a generative OS that….

RT @lockonlvange: 👇this nice guy❤️will help us present CodeI/O ( at Oral session 6A Applications in Agents and Codi….

RT @yihengxu_: Attending #ICML2025 🇨🇦 this week! . Will be presenting Aguvis ( on July 15 at 11am, and joining Comp….

RT @gm8xx8: Reinforcement Learning with Action Chunking. Q-Chunking improves offline-to-online RL by operating in a temporally extended act….

RT @james_y_zou: 📢New conference where AI is the primary author and reviewer! Current venues don't allow AI-writte….

RT @sivil_taram: 🚀 Check out our recent work Afterburner: Reinforcement Learning demonstrating super powerful self-improving code efficienc….

RT @FaZhou_998: MegaMath has been accepted to @COLM_conf 2025🥳 Hoping you find our data useful!

RT @NasosGer: 1/n Multi-token prediction boosts LLMs (DeepSeek-V3), tackling key limitations of the next-token setup:.• Short-term focus.•….

RT @sansa19739319: 🤖Can diffusion models write code competitively?.Excited to share our latest 7B coding diffusion LLM!!💻. With DiffuCoder,….