3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark Paper • 2412.07825 • Published 14 days ago • 12
ViTamin: Designing Scalable Vision Models in the Vision-Language Era Paper • 2404.02132 • Published Apr 2 • 2
SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis Paper • 2409.07556 • Published Sep 11 • 2
SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer Paper • 2409.08425 • Published Sep 12 • 9
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer Paper • 2409.10819 • Published Sep 17 • 18
Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models Paper • 2408.06663 • Published Aug 13 • 15
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models Paper • 2407.05502 • Published Jul 7
Rethinking Model Evaluation as Narrowing the Socio-Technical Gap Paper • 2306.03100 • Published Jun 1, 2023
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models Paper • 2407.05502 • Published Jul 7
Improving Context-Aware Preference Modeling for Language Models Paper • 2407.14916 • Published Jul 20 • 4
RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation Paper • 2406.14764 • Published Jun 20 • 4
The Validity of Evaluation Results: Assessing Concurrence Across Compositionality Benchmarks Paper • 2310.17514 • Published Oct 26, 2023
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees Paper • 2404.08417 • Published Apr 12 • 1
RE-Adapt: Reverse Engineered Adaptation of Large Language Models Paper • 2405.15007 • Published May 23 • 1
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting Paper • 2405.15125 • Published May 24 • 5
Generative Echo Chamber? Effects of LLM-Powered Search Systems on Diverse Information Seeking Paper • 2402.05880 • Published Feb 8 • 3