AI研究論文デイリー

Spectra: A Comprehensive Study of Ternary, Quantized, and FP16 Language Models

GoldFinch: High Performance RWKV/Transformer Hybrid with Linear Pre-Fill and Extreme KV-Cache Compression

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

E5-V: Universal Embeddings with Multimodal Large Language Models

LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Patch-Level Training for Large Language Models

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

IMAGDressing-v1: Customizable Virtual Dressing

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos

Case2Code: Learning Inductive Reasoning with Synthetic Data

Audio Conditioning for Music Generation via Discrete Bottleneck Features

Splatfacto-W: A Nerfstudio Implementation of Gaussian Splatting for Unconstrained Photo Collections

ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter

AUITestAgent: Automatic Requirements Oriented GUI Function Testing

NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models

Practical Unlearning for Large Language Models

The Art of Saying No: Contextual Noncompliance in Language Models

Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection

Towards Understanding Unsafe Video Generation