🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Knowledge Conflict gets accepted in #ICLR24 #Spotlight! We updated more results on 5 open- and 3 close-source LLMs and found highly receptiveness & confirmation bias exist widely! Check it out: openreview.net/forum?id=auKAU…

Our entity linking work has been accepted by #EACL2024. Check our work: Ameli: Enhancing Multimodal Entity Linking with Fine-Grained Attributes (arxiv.org/pdf/2305.14725…). Congratulations to all collaborators! The dataset, code, and checkpoints will be released soon.

Vision-Flan Scaling Human-Labeled Tasks in Visual Instruction Tuning Despite vision-language models' (VLMs) remarkable capabilities as versatile visual assistants, two substantial challenges persist within the existing VLM frameworks: (1) lacking task diversity in pretraining

🚀 Excited to introduce my internship work at Apple MLR : Many-to-many Image Generation with Auto-regressive Diffusion Models (arxiv.org/abs/2404.03109). Exploring the paradigm for domain-general multi-image to multi-image generation.

Can Text-to-Image models understand common sense? 🤔 Can they generate images that fit everyday common sense? 🤔 tldr; NO, they are far less intelligent than us 💁🏻‍♀️ Introducing Commonsense-T2I 💡 zeyofu.github.io/CommonsenseT2I/, a novel evaluation and benchmark designed to measure

Thank you for the great work! Will definitely check it out.

Ever wondered if style lexicons still play a role in the era of LLMs? 🤔 We tested 13 established and 63 novel language styles across different LLMs. 🧠✨ It turns out lexicons are still crucial for style understanding! But how can we better leverage this lexical knowledge? Our

📢✨ I am recruiting 1-2 PhD students at Virginia Tech this cycle. If you are interested in efficient model development (including model merging, parameter-efficient fine-tuning & transfer learning), instruction tuning, advanced reasoning, LLMs-as-judges, etc., please apply!!

🔥Thrilled to announce ReFocus, our latest work led by Xingyu Fu that teaches MLLMs to generate “visual thoughts” 🧠 via visual editing on tables and charts 📊 to improve reasoning. Huge thanks to all the amazing co-authors! 🙌

Refocus🔍 Visual reasoning for Tables and Charts with Edits Happy to share ReFocus accepted at #ICML2025. We’ve open-sourced code and training data: zeyofu.github.io/ReFocus/ ReFocus enables multimodal LMs to better reason on Tables and Charts with visual edits. It also provides

📢We conduct a systematic study to demystify the synergy between SFT and RL for reasoning models. The result? We trained a 7B model - AceReason-Nemotron-1.1, significantly improved from version 1.0 on math and coding benchmarks. ✅AIME2025 (math): 53.6% -> 64.8% ✅LiveCodeBench