dLLM: Simple Diffusion Language Modeling
Paper โข 2602.22661 โข Published โข 153
ebisuke PRO
ebisuke
AI & ML interests
None yet
Recent Activity
reacted to AkimfromParis's post with โค๏ธ about 17 hours ago
๐ธ ๐๐ฅ๐๐ฃ ๐
๐๐ฅ๐๐ฃ๐๐จ๐ ๐๐๐ ๐๐๐๐๐๐ง๐๐ค๐๐ง๐ ๐2 ๐ค๐ฃ ๐๐ช๐๐๐๐ฃ๐ ๐๐๐๐ ๐ฏ๐ต // ๐ธ ใใฎใณใฐใใงใคใน็ใ ๐ข๐ฝ๐ฒ๐ป ๐๐ฎ๐ฝ๐ฎ๐ป๐ฒ๐๐ฒ ๐๐๐ ๐๐ฒ๐ฎ๐ฑ๐ฒ๐ฟ๐ฏ๐ผ๐ฎ๐ฟ๐ฑ ๐ฉ๐ฎ ใๅ
ฌ้ ๐ฏ๐ต
I am thrilled to announce the launch of version 2 of the ๐๐ฅ๐๐ฃ ๐
๐๐ฅ๐๐ฃ๐๐จ๐ ๐๐๐ ๐๐๐๐๐๐ง๐๐ค๐๐ง๐. This initiative is driven by the "Fine-tuning and Evaluation" team, led by Professor Miyao at the The University of Tokyo, under the Research and Development Center for Large Language Models (LLMC) at Japanโs National Institute of Informatics (NII).
๐๐ฉ๐ง๐๐ฉ๐๐๐๐ ๐๐ฃ๐ ๐ฉ๐๐๐๐ฃ๐๐๐๐ก ๐ช๐ฅ๐๐ง๐๐๐๐จ:
- Our new backend features eight A100 GPUs, enabling the evaluation of open-source models of more than 100B parameters.
- Submissions now require a Hugging Face Hub login to ensure accountability.
- We have added metrics for evaluation time, COโ emissions (thx to Code Carbon ๐ฑ ), alongside reasoning capabilities.
๐ฟ๐๐ฉ๐๐จ๐๐ฉ๐จ ๐๐ฃ๐ ๐๐ซ๐๐ก๐ช๐๐ฉ๐๐ค๐ฃ ๐จ๐ฉ๐๐ฃ๐๐๐ง๐๐จ:
- New datasets cover reasoning, mathematics, exams, and instruction following.
- Math evaluations now span from grade-school levels to expert-tier challenges (GSM8K, PolyMath, AIME).
- While integrating English-heavy and multilingual benchmarks (including Humanityโs Last Exam, GPQA, and BBH in both English and Japanese), we continue to prioritize unique Japanese cultural datasets.
https://huggingface.co/spaces/llm-jp/open-japanese-llm-leaderboard-v2
ใฉใใใ้กใ่ดใใพใ๏ผ๐Organizations
None yet
upvoted a paper about 2 months ago
upvoted a paper 8 months ago
upvoted a paper 11 months ago
upvoted 2
papers over 1 year ago
upvoted 5
papers almost 2 years ago
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy
Paper โข 2406.20095 โข Published โข 18
Adam-mini: Use Fewer Learning Rates To Gain More
Paper โข 2406.16793 โข Published โข 69
DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
Paper โข 2406.11617 โข Published โข 10
RVT-2: Learning Precise Manipulation from Few Demonstrations
Paper โข 2406.08545 โข Published โข 8
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
Paper โข 2406.02523 โข Published โข 12
upvoted an article almost 2 years ago
Article
Space secrets security update
โข
52
upvoted a paper almost 2 years ago
upvoted 4
papers about 2 years ago
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
Paper โข 2404.13013 โข Published โข 31
FuseChat: Knowledge Fusion of Chat Models
Paper โข 2402.16107 โข Published โข 39
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
Paper โข 2402.12226 โข Published โข 45
Anything in Any Scene: Photorealistic Video Object Insertion
Paper โข 2401.17509 โข Published โข 17
upvoted 4
papers over 2 years ago
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Paper โข 2401.10774 โข Published โข 60
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
Paper โข 2401.02117 โข Published โข 33
PockEngine: Sparse and Efficient Fine-tuning in a Pocket
Paper โข 2310.17752 โข Published โข 15
BitNet: Scaling 1-bit Transformers for Large Language Models
Paper โข 2310.11453 โข Published โข 107