#LLM
Curated coverage on «LLM»: releases, research, benchmarks, open-source.
DuET cuts piano-to-score transcription error from 6.56% to 3.64%
Researchers from the National University of Singapore have unveiled DuET, a transformer for automatic piano-to-score transcription. On the Gangqinpu dataset, the…
LexFrame reads LLM hidden states: 0.97 coherence against a lens ceiling of 0.30
A new method reads hidden states through the model's own remaining layers. On SmolLM3-3B and OLMo3-7B it reaches 0.97 coherence, while fixed lenses top out at…
OmniXRef: A Unified Framework for Video Editing with Multimodal References
Adobe Research has unveiled OmniXRef, a framework for video editing with multimodal references. It lets creators combine text, images, and video to control motion…
Scene-Designer Learns to Design and Critique 3D Scenes from Text Using 50,000 Examples
RAP compiles 25,000 paper-poster pairs to teach AI how to lay out posters in HTML/CSS
Meta to Use Muse Spark 1.3 in Medical Research, Promises a 10x Speedup
Apple and CMU Speed Up AI Agents 10x by Replacing Reasoning with Selection
KTransformers Moves Part of the MoE Computation to the CPU and Eliminates Weight Transfers During Fine-Tuning
The KTransformers team proposes running MoE experts directly on the CPU during fine-tuning, aiming to tune open-source giants like DeepSeek-V4 and Kimi-K3 without a…
Kling 4.0 Launches With Native 30-Second Video Generation and Combat Scenes
Kling 4.0 launched on the evening of October 15. The model generates 30 seconds of video in a single pass and takes on battle scenes with cavalry, sieges and crowds.
ProD Stops AI Agents From Looping: Tested on 8 Models (0.6B–8B)
ECHO: Multi-Step Forecasting Without Add-Ons, Half the Cost of MTP
UniAVC: Joint Audio-Video Synthesis via Asymmetric Noise Scheduling
Groq Launches Meta Muse Spark Open: 816B Parameters and 350+ Tokens/s
CoworkEnv synthesizes training environments for AI coworkers: Qwen3-VL-8B jumps from 46.6 to 64.1
CoworkEnv is a new framework for training compact AI agents that work with tools in multi-step scenarios. It combines task generation, validation, and repair — and…
Manifold AI Tops RoboDojo, Beating GPT-6-Astra and GR00T-N1.7
China's Manifold AI unveiled R²SI and took first place in the RoboDojo Agent Track, ahead of GPT-6-Astra and NVIDIA GR00T-N1.7, three months after releasing its…