AI Research Papers Daily

nabla^2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

Instruction Pre-Training: Language Models are Supervised Multitask Learners

The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing

HARE: HumAn pRiors, a key to small language model Efficiency

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs

MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities

Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps

GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks

PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

LiveMind: Low-latency Large Language Models with Simultaneous Inference

Improving Visual Commonsense in Language Models via Multiple Image Generation

Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level

REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic Images

From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP

A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models

Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models