[FEEDBACK] Daily Papers
Note that this is not a post about adding new papers, it's about feedback on the Daily Papers community update feature.
How to submit a paper to the Daily Papers, like @akhaliq (AK)?
- Submitting is available to paper authors
- Only recent papers (less than 7d) can be featured on the Daily
Then drop the arxiv id in the form at https://huggingface.co/papers/submit
- Add medias to the paper (images, videos) when relevant
- You can start the discussion to engage with the community
Please check out the documentation
We are excited to share our recent work on MLLM architecture design titled "Ovis: Structural Embedding Alignment for Multimodal Large Language Model".
Paper: https://arxiv.org/abs/2405.20797
Github: https://github.com/AIDC-AI/Ovis
Model: https://huggingface.co/AIDC-AI/Ovis-Clip-Llama3-8B
Data: https://huggingface.co/datasets/AIDC-AI/Ovis-dataset
we are excited to share our work titled "Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models" : https://arxiv.org/abs/2406.12644
Hello AK and HF Team,
We would to add our recent paper "MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem"
Mathematical modeling is more than reasoning โ it requires open-ended analysis, abstraction, and principled formulation. This work introduces MM-Agent, a large language model (LLM)-powered agent framework designed to tackle real-world mathematical modeling tasks end-to-end.
Key highlights:
๐ Proposes MM-Bench: 111 curated problems from MCM/ICM (2000โ2025), across physics, biology, economics, etc.
๐งฉ MM-Agent decomposes modeling into 4 expert-inspired stages:
Problem Analysis โ Model Formulation โ Problem Solving โ Report Generation
๐ Outperforms baselines by 11.88% over expert-written solutions using GPT-4o, while costing just $0.88 and 15 minutes per task.
๐ Helped two undergrad teams win Finalist Award (top 2%) in MCM/ICM 2025.
๐ Paper: https://arxiv.org/abs/2505.14148
๐ป Code: https://github.com/usail-hkust/LLM-MM-Agent
Hi, everyone! We are happy to share with you our work SVD-Free Low-Rank Adaptive Gradient Optimization for Large Language Models.
We focus on the low-rank compression of optimizer states and propose replacing the expensive SVD decomposition with a fixed orthogonal matrix that comes from the Discrete Consine Transformation (DCT).
In our work we couple the DCT matrix with a theoretically-justified approach to choose the most appropriate columns from the DCT matrix that minimize the reconstruction error for each gradient matrix G and obtain a dynamic projection matrix tailored to each gradient G.
Our numerical results show that DCT matrix not only recovers the performance of existing low-rank optimizers, but also reduces the running time by 20% and memory usage for large models, both for pretraining and finetuning.
๐ Paper: https://arxiv.org/pdf/2505.17967
๐ Code: soon to appear in https://github.com/IST-DASLab/ISTA-DASLab-Optimizers via pip
HI, all! We are thrilled to present our work: VerIF: Verification Engineering for RL in Instruction Following.
In this work, we introduce VerIF, a new verification method for RL in instruction following. RL with VerIF significantly improves the instruction-following capabilities of LLMs. TULU3+VerIF achieves SoTA performance across models with similar sizes.
Our paper: https://arxiv.org/abs/2506.09942
Our repo: https://github.com/THU-KEG/VerIF
Why am I getting error of not finding paper on arXiv when giving the correct identifier?
ุณูุงู