Can LLMs Correct Historical OCR Without Rewriting History?
emanuelaboros
• • 2NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Stablecoin Risk Decision Engine - Dispute Lifecycle Management- Hugging Face model announcement
sriram1983007
• • 1Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
tiiuae
• • 20Falcon OCR Arabic: 270M Parameters State-of-the-Art Arabic OCR
tiiuae
• • 16ViDiHand: The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Xingang-Pan
• • 4Understanding Prism: Dynamic Sparse Attention for Joint Video-Audio Generation
a2aprotocol
• Build a Tiny Language Model, Day 1: Data and Tokenizer
ericmey
• • 1Reducing dropped tokens in a small MoE model
kotlarmilos
• Allocating latent KV-cache memory across transformer layers
kotlarmilos
• Shrinking my transformer's KV cache with a KL calibration budget
kotlarmilos
• FiftyOne Now Reads LeRobot: 50 Embodiments, 497 Episodes, One Indexed Dataset
harpreetsahota
• • 4How LLM Inference Actually Works: From Prompt Tokens to the Next Token
prismberry-technologies
• • 1CiberIA Expected Cognitive Profile Fast: CLEF
gcjordi
• OpenAI Decisions API Luna Model: A Practical Guide
sora-2
• Rewarding fact fidelity with an LLM judge in GRPO: lessons from 38,000 judged rewrites
jialinyyzz
• • 3MultiMatte: Keep What You Want, Cut the Rest
feyninc
• • 1Decoding LLM Alignment: A Concise Guide for GRPO and its variants
Sneha7
• • 5🤖 RLJF: Reinforcement Learning from Jev Feedback
jgalego
• • 1Aletheia and Algorithms: Why AI Cannot Uncover Truth
thevasilis
• • 1What Agents Do: A Large-Scale Public Dataset of Agent Runs
michalshmu
•