NICE AI Talk

NICE AI Talk No. 165🤩 Inviting Jian Yang to explore the frontier of industrial code: Can AI truly learn to "think" like a hardware engineer? 🤔 ​Time: PDT 2026.04.18 (Saturday) 18:30–19:30 | EDT 21:30–22:30 Register to watch live: Luma Event 📩 luma.com/syjjk4gx ​ The InCoder-32B series tackles modern industrial code from chip design to GPU optimization by introducing the first unified foundation model purpose-built for these high-stakes environments. By combining large-scale industrial code pretraining with real-world validation tools, it establishes a new open-source baseline for serious engineering tasks. Moving beyond simple code generation. Jian's team built an Industrial Code World Model (ICWM) with 96.7% prediction accuracy, refining reasoning through Error-Driven Chains of Thought (ECoT). The result is a system that dynamically adapts its reasoning depth—from concise fixes to long-form, multi-step debugging traces (91 to 19K tokens)—achieving 81.3% on LiveCodeBench. 📽️Guest Profile: Jian Yang, Ph.D. and Assistant Professor at Beihang University. He has published 100+ publications among ICLR, NeurIPS, ACL, EMNLP etc top-tier venues, and served as a Senior Area Chair and Senior Program Committee member for NeurIPS, Association for Computational Linguistics, and Association for the Advancement of Artificial Intelligence (AAAI). His work bridges the gap between high-level LLM reasoning and the rigid constraints of real-world "cold code" like Verilog and CUDA. Paper: arxiv.org/abs/2604.03144 arxiv.org/abs/2603.16790 Huggingface: huggingface.co/collections/Mu… ​#AI #SoftwareEngineering #IndustrialCode #LLMs #ChipDesign #Hardware #NICEAITalk #Academic

NICE PODCAST🤩Inviting Researcher Wenyue Hua @HuaWenyue31539 to step beyond pure tech: How does she leverage interdisciplinary thinking to tackle Agent adoption's toughest challenges? 🤔 Time: EST 2026.04.17 (Friday) 22:00-23:00 Register to watch live: luma.com/d13m4qcm Finding the optimal balance between models, tools & budget. Building "insured" #trust standards for Agents, inspired by financial risk control. 🛡️ 👩‍🎓From UCLA (Math + Philosophy) → Linguistics to CS PhD → Microsoft Research. Her winding path seeks universal solutions across disciplines. 🧠In an era of tech acceleration, what can a humanities lens bring to cold code? 📺watch live: youtube.com/live/DZ5j0uX2j… The relevant work will be mentioned in the podcast🥳 🌟AgentOpt Homepage: agentoptimizer.github.io/agentopt/ Github: github.com/AgentOptimizer… Blog: agentoptimizer.github.io/agentopt/blog/… 🌟Quantifying Trust Title: Quantifying Trust: Financial Risk Management for Trustworthy AI Agents arXiv: arxiv.org/pdf/2604.03976 Github: github.com/t54-labs/Agent… Host: Enyu Zhou, PhD at Fudan University #AI #Agents #Interdisciplinary #podcast #industry #academic

NICE TALK 157 🥳 invites Dr. Xiaoxuan Wang, PhD at UCLA, to talk about a unified framework for stable agentic reinforcement learning. Talk Time⏰EST 4.3⏰21:30~22:30 📌Watch live: youtube.com/live/XBwKxsG3J… 📌Register on Luma: luma.com/wohpla9w ⭐️They proposed one analytical framework ARLArena, and conducted an in-depth analysis across four key dimensions: Loss Aggregation, Importance Sampling (IS) Clipping, Trajectory Filtering, and Advantage Design. 🤖 One unified RL method, SAMPO, which integrates three core mechanisms: 1⃣sequence-level clipping to ensure baseline stability 2⃣fine-grained advantage signals (turn-level advantages) to improve credit assignment 3⃣dynamic trajectory filtering to further enhance training data quality. paper: arxiv.org/pdf/2602.21534 github: github.com/WillDreamer/AR… #AI #agent #LLM #generative #RL #reasoning

NICE Talk 158🌟 invites Yinjie Wang (👤 homepage: yinjjiew.github.io), Ph.D. student at the University of Chicago, to share insights on OpenClaw-RL — an agent that improves the more you use it. Talk Time ⏰ PDT 04.04 18:30–19:30 EDT 04.04 21:30–22:30 📌 Watch live: YouTube: youtube.com/live/xEhRXqDwF… 😊 Register: luma.com/hfipfd5w Key highlights: 🧠 What if your model could learn and evolve from every interaction after deployment? ⚙️ OpenClaw-RL is a novel RL framework — deploy your model on it, and it automatically and continuously self-improves through real-world usage. 🚀 Combines GRPO + On-policy Distillation, turning the entire history of model-user-environment interactions into powerful RL training signals. 🤖 The result: personal agents that don't stay static — they grow smarter and more adaptive the more they are used. 🔍 Validated through creative experiments demonstrating efficient self-optimization for personal agents. paper: arxiv.org/abs/2603.10165 #AI #Agent #LLM #RL #ReinforcementLearning #SelfEvolving #OpenClawRL #GRPO #PhDLife #AIResearch

NICE Talk 156 🌟 invites Dr. Yifu Qiu @yifuqiu98, PhD candidate at the University of Edinburgh, jointly supervised at Cambridge University. 🥳We will talk about models' self-improving world modelling via latent actions! Talk Time⏰EST 4.3⏰9:00~10:00 📌Watch live: youtube.com/live/Xs_FgZUfU… 📌Register on Luma: luma.com/qyapi22d In the internal world modeling process of VLMs and LLMs, we often face these challenges: 🙃Difficulty in unified modeling across diverse modalities 🤖Limited interpretability of latent actions between states 💡Challenges in acquiring accurate action annotation data 📈Difficult to autonomously complete learning through rollouts The ability to internally model the world is essential: predicting next states from current states and actions. SWIRL🍥, a self-improving framework that treats actions as latent variables and alternates optimization between a forward world model and an inverse dynamics model to learn solely from state sequences. SWIRL🍥 achieves cross-modal SOTA, improving AURORA-BENCH by 16%, ByteMorph by 28%, WORLD-PREDICTION-BENCH by 16%, and STABLETOOL-BENCH by 14%. paper: arxiv.org/pdf/2602.06130 github: github.com/yfqiu-nlp/swirl #worldmodel #multimodal #AI #agent #LLM #generative #RL #reasoning

NICE Talk 154🌟 invites Wei Fu (👤 homepage: garrett4wade.github.io ), Ph.D. student at Tsinghua University, to share insights on RL infrastructure for next-generation AI systems. Talk Time ⏰ PST 03.28 06:00–07:00 EST 03.28 09:00–10:00 📌 Watch live: YouTube: youtube.com/watch?v=C-1po0… 😊 Register: luma.com/ym4y7jwq Key highlights: 🧠 Reinforcement Learning (RL) has become a central focus in the LLM community, and Agentic RL is rapidly shaping the 2026 landscape. ⚙️ This talk dives into RL infrastructure through a deep-dive of AReaL 1.0, a large-scale asynchronous RL system. 🚀 AReaL enables zero-code integration for online RL training—simply connect via base URL and API key to train and evolve agent applications. 🤖 Supports a wide range of agent use cases, including emerging frameworks like OpenClaw. 🔍 Discussion on challenges and opportunities in RL Infra, and how AReaL is evolving in the era of agent-driven AI. paper: github.com/inclusionAI/AR… #AI #agent #LLM #RL #ReinforcementLearning #GenerativeAI #Infrastructure

NICE Talk 153🌟 invites Peng Yu, a PhD student at SJTU, to discuss Structured In-context Environments (SIE) for enhancing the model's reasoning environment. Talk Time⏰PST 3.27 20:00~21:00 📌 Watch live: youtube.com/live/i43hXQnDs… Register on Luma: luma.com/n09s3lti 🙃Traditional mathematical or coding environments rely heavily on expensive expert annotations, while the skills learned in game-like environments are difficult to generalize. 🧐 An ideal LLM Reasoning training environment must simultaneously possess three core features: Scalability, support for Generalizable Reasoning, and Verifiability. ☺️The SIE framework proposes to automatically construct an inference environment from massive structured data, such as knowledge graphs. paper: openreview.net/pdf?id=CicK2lJ… #AI #agent #LLM #generative #RL #reasoning

NICE Talk 151🌟 invites Jundong Xu @nigualjiadapubu, a PhD student at NUS, to discuss step-level logical validation to prevent correct answers from flawed reasoning. Talk Time⏰PST 3.22 20:00~21:00 📌 Watch live: youtube.com/live/dLNEsNG3H… Register on Luma: luma.com/o02ruqhj Key findings: 🧐LogicReward trains LLMs using step-level logical validation to prevent correct answers from flawed reasoning. It combines autoformalization with soft unification and theorem-prover checks to ensure the faithfulness of reasoning. 🤠This approach improves performance across benchmarks and generalizability to unseen tasks. paper: arxiv.org/pdf/2512.18196 #AI #agent #LLM #generative #RL #reasoning

NICE Talk 150🌟 invites Yufan Zhuang @yufan_zhuang, a PhD student at UCSD, to discuss LLM self-improving during test-time. Talk Time⏰EST 3.22 21:00~22:00 📌 Watch live: youtube.com/live/giD-VwGrw… Register on Luma: luma.com/03xnrfuv Key findings are counterintuitive: 🧐The Test-time Recursive Thinking (TRT) framework enables LLMs to self-improve reasoning through iterative knowledge accumulation, combining strategic rollout generation, self-verification-based solution selection, and contrastive failure analysis without external supervision. 😎TRT achieves significant accuracy gains: open-source models reach 100% on AIME benchmarks, while closed-source models improve by 10.4～14.8 percentage points on LiveCodeBench’s hardest problems through self-generated test execution and adaptive exploration strategies. paper: arxiv.org/pdf/2602.03094 #AI #agent #LLM #generative #scaling

NICE Talk 148🌟 invites @emilianopp_, a PhD student at Mila-Quebec & Université de Montréal, to discuss how LLMs can learn from privileged information during training — without needing it at test time. 📖 Paper: Privileged Information Distillation for Language Models — [arxiv.org/pdf/2602.04942] ⏰ Time: 3.20 (Fri) 9:00 PM - 10:00 PM EDT 3.20 (Fri) 6:00 PM - 7:00 PM PDT 📌 Register: luma.com/dll9x6f5 📌 Watch live: youtube.com/watch?v=SUb4M7… ✨This talk is hosted by @Haolun_Wu0203, Ph.D. at Mila & McGill What if your model could train with a "cheat sheet" — but still ace the test without it? Emiliano presents Privileged Information Distillation, a unified post-training framework that bridges the gap between hinted training and non-privileged inference. ⭐ Key findings: 🧐 Privileged information during training significantly boosts LLM performance — but design choices matter enormously for generalization; 🤠 A variational framework + on-policy distillation outperforms strong baselines including SFT + GRPO; 🤪 Most surprisingly, not all privileged information is equal — the right hints incentivize generalization, while the wrong ones don't. #AI #LLM #PrivilegedInformation #Distillation #PostTraining #Reasoning #NICE #NexusForIntelligence

NICE Talk 145🌟 invites Xuan Liu @XuanLiu888, a PhD student at UCSD, to discuss whether AI can truly reproduce human behavior through HumanStudy-Bench. Time ⏰PST 3.14 19:00~20:00 ⏰EST 3.14 22:00~23:00 📌 Watch live: YouTube livestream: youtube.com/live/rY5uwNTig… Register on Luma: luma.com/2o4hy5v6 Key findings are counterintuitive: 🧐model scale ≠ more human-like: the same model with different agent designs varied by 35%+; 🤠no universal optimal template: each model has its own "best recipe"; 🤪Most surprisingly, telling it "you are a human" sometimes makes it less human, not more. Related Work: - CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments — ACM CHI 2026 🏆 Best Paper Award —[arxiv.org/abs/2509.13588] - CogMir: Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View — ICLR 2025 —[arxiv.org/abs/2405.14744] #AI #agent #LLM #human #benchmark #generative

NICE Talk 144🌟 invites Ming Xu @Ming_happylife , a postdoctoral researcher at NUS, to discuss agentic AI for scalable and reliable cyber defense. Time ⏰PST 3.12 19:00~20:00 ⏰EST 3.12 22:00~23:00 📌 Watch live: Youtube livestream: youtube.com/live/x4sfm513t… Register on luma: luma.com/ey9hdcsz 🤩 RulePilot employs an intermediate representation (IR) to simplify complex rule configurations into standardized formats, enhancing both accuracy and efficiency. 🧐 RulePilot shows a 107.4% improvement in text similarity to established rules and effective detection in practical trials. #AI #SIEM #CyberDefense #Security

We would like to make a clarification to the poster and offer our sincere apologies: ThunderAgent is not the first pioneering work to apply program-level abstraction to system optimization. This clarification is made in the interest of maintaining rigor in academic and technical discussions, and to express proper respect to all the researchers who have worked diligently in this area.

NICE Talk 141🌟invites Ph.D. at Georgia Tech Hao Kang @GT_HaoKang to discuss ThunderAgent: 4× Faster LLM Agent Inference! Time ⏰ PST 3.07 18:00–19:00 ⏰ EST 3.07 21:00–22:00 ⏰ Beijing 3.08 10:00–11:00 Watch live: youtube.com/live/kHw6LZsXc… Register: luma.com/ezn8ho93 In this talk, the speaker will talk about: 🚀 How can we make LLM agent workflows faster, simpler, and more robust? ❌ Traditional request-level engines (vLLM, SGLang) struggle with KV cache thrashing, memory imbalance, and resource leaks. ✅ ThunderAgent introduces Program Abstraction, treating multi-step agent workflows as programs, unifying GPU, CPU, and remote tool scheduling. With just two lines of code, ThunderAgent boosts inference throughput by 1.5–3.6×, rollout throughput by 1.8–3.9×, and saves 4.2× disk space, while ensuring high concurrency stability. Join us to explore a principled, program-level approach to distributed agent inference and RL rollouts. #AI #LLM #AgenticAI #ReinforcementLearning #DistributedSystems #ProgramAbstraction #ThunderAgent

NICE Talk 142🌟invites Researchers Tianxin Wei @wei_tianxin, Tingwei Li, and Zhining Liu to discuss the next step #reasoning: the Action-Driven and Self-Evolving Agentic Reasoning. Time⏰PST 3.8 19:00~20:00 Watch through this link: luma.com/ezt73jm8 The categories of Agentic Reasoning: 1⃣foundation agent reasoning 2⃣self-evolving agent reasoning 3⃣multi-agent cooperative reasoning The two reasoning forms analyzed from the system constraints and optimization methods: in-context reasoning and post-train reasoning #AI #LLM #models #context #generative #AgenticAI #agents