🌠Flow Matching Meets Biology and Life Science: A Survey
Flow matching is emerging as a powerful generative paradigm. We comprehensively review its foundations and applications across biology & life science🧬
📚Paper: arxiv.org/abs/2507.17731
💻Resource: github.com/Violet24K/Awes…
🧠Let’s teach LLMs to learn smarter, not harder💥[arxiv.org/pdf/2506.06972]
🤖How can LLMs verify complex scientific information efficiently?
🚀We propose modular, reusable atomic reasoning skills that reduce LLMs’ cognitive load to verify scientific claims with little data.…
😲 Not only reasoning?! Inference scaling can now boost LLM safety!
🚀 Introducing Saffron-1:
- Reduces attack success rate from 66% to 17.5%
- Uses only 59.7 TFLOP compute
- Counters latest jailbreak attacks
- No model finetuning
On the AI2 Refusals benchmark.
📖 Paper:…
Today, we introduce our hashtag#CIKM2025 Industry Day Chairs 👏
Jingren Zhou, Soonmin Bae, and Xianfeng Tang are leading this program connecting academia and industry.
🤖 New preprint: We propose ten principles of AI agent economics, offering a framework to understand how AI agents make decisions, influence social interactions, and participate in the broader economy.
📜 Paper: arxiv.org/abs/2505.20273
🚨 ICML ’25 SPOTLIGHT 🚨
Taming Knowledge Conflict in Language Models
🤔 Why does your LLM sometimes echo the prompt but other times rely on its “built-in” facts?
🎭 Can we toggle between parametric memory and fresh context without fine-tuning?
🔬 Curious about LLM internals,…
🔬Graph Self-Supervised Learning Toolkit
🔥We release PyG-SSL, offering a unified framework of 10+ self-supervised choices to pretrain your graph foundation models.
📜Paper: arxiv.org/abs/2412.21151
💻Code: github.com/iDEA-iSAIL-Lab…
Have fun!
🔍New findings of knowledge overshadowing! Why do LLMs hallucinate over all true training data? 🤔Can we predict hallucinations even before model training or inference?
🚀Check out our new preprint: [arxiv.org/pdf/2502.16143] The Law of Knowledge Overshadowing: Towards…
🚀 New Paper Alert! 🚀
LLMs struggle with self-correction like O1/R1 because models lack judgment on when to revise vs. when to stay confident. We introduce self-rewarding reasoning LLM, a reasoning framework that:
✅ integrates generator and generative RM into a single LLM.
✅…
📈 Your time-series-paired texts are secretly a time series!
🙌 Real-world time series (stock prices) and texts (financial reports) share similar periodicity and spectrum, unlocking seamless multimodal learning using existing TS models.
🔬 Read more: arxiv.org/abs/2502.08942
Congrats to Hanrong, our publication "Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents" has been accepted to ICLR 2025 (@iclr_conf). An unforgettable rebuttal for three weeks!
Paper Link: arxiv.org/abs/2410.02644
563 Followers 320 FollowingPostdoc@UIUC, advised by Prof. Heng Ji @hengjinlp and Prof. Chengxiang Zhai. Robust and trustworthy LLMs. LLM hallucination. LLM knowledge. LLM reasoning.
36 Followers 17 FollowingPrinciple Investigators: Prof. Hanghang Tong and Prof. Jingrui He @UofIllinois.
Data-Driven AI/ML | Data Mining | Heterogeneity and Trustworthy
1K Followers 1K FollowingAssistant Professor @VanderbiltU; Network and Data Science Lab @VU_NDS_Lab; Social Network Analysis, Graph Neural Networks, Data Science for Social Good ♻️
15K Followers 50 FollowingEMNLP 2025 - The 2025 Conference on Empirical Methods in Natural Language Processing, 2025
Hashtag: #EMNLP2025
Dates: November 5-9
Submission Deadline: May 19th
118 Followers 33 FollowingAssistant Professor of Computer Science at the University of Illinois Urbana-Champaign. Games · VR · HCI. @MIT, @Princeton, @UAlberta alum.
975 Followers 584 FollowingAssistant Professor of Computer Science, Johns Hopkins University @JHUCompSci @HopkinsDSAI working on computational genomics + ML
563 Followers 320 FollowingPostdoc@UIUC, advised by Prof. Heng Ji @hengjinlp and Prof. Chengxiang Zhai. Robust and trustworthy LLMs. LLM hallucination. LLM knowledge. LLM reasoning.
20K Followers 452 Followingphysics of language models @ Meta (FAIR, not GenAI)
🎓:Tsinghua Physics — MIT CSAIL — Princeton/IAS
🏅:IOI x 2 — ACM-ICPC — USACO — Codejam — math MCM
36 Followers 17 FollowingPrinciple Investigators: Prof. Hanghang Tong and Prof. Jingrui He @UofIllinois.
Data-Driven AI/ML | Data Mining | Heterogeneity and Trustworthy
9K Followers 2K FollowingAssociate professor of @umdcs @umiacs @ml_umd at UMD. Researcher in #AI/#ML, AI #Alignment, #RLHF, #Trustworthy ML, #EthicalAI, AI #Democratization, AI for ALL.
2K Followers 288 FollowingAssistant Professor at UIUC CS | Previously @MSFTResearch @Stanford | Creator of Puffer (400k users) | Illinois Networked Systems + AI Lab.
1K Followers 592 FollowingResearch Scientist at @AIatMeta | Ph.D. from @IllinoisCDS | Working on #GeometricDeepLearning #SequenceModeling #ProbabilisticGraphicalModel
712K Followers 288 FollowingTogether with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.
6K Followers 782 Followingreasoning research @OpenAI 🍓 | UCLA CS PhD (‘21-‘24) | Ex. Microsoft Research (AI Frontiers), Meta (FAIR), NVIDIA Research (LPR)
19K Followers 1K Following@OpenAI Language agents (ReAct, Reflexion, Tree of Thoughts, SWE-agent, CoALA) for digital automation (WebShop, SWE-bench, tau-bench)
109K Followers 166 FollowingUPMC Professor of Computer Science @ CMU, President Elect ICML Board, VP of Research @ Meta (Multimodal LLMs, AI Agents), ex-Director of AI research at @Apple