SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models Paper • 2503.07605 • Published 4 days ago • 63
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding Paper • 2502.08946 • Published 30 days ago • 184
Closed-loop Long-horizon Robotic Planning via Equilibrium Sequence Modeling Paper • 2410.01440 • Published Oct 2, 2024 • 4
SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios Paper • 2410.01481 • Published Oct 2, 2024 • 3
InfiniPot: Infinite Context Processing on Memory-Constrained LLMs Paper • 2410.01518 • Published Oct 2, 2024 • 3
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data Paper • 2410.00296 • Published Oct 1, 2024 • 5
HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration Paper • 2410.01723 • Published Oct 2, 2024 • 5
EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis Paper • 2410.01804 • Published Oct 2, 2024 • 7
EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control Paper • 2410.00316 • Published Oct 1, 2024 • 7
BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation Paper • 2410.01171 • Published Oct 2, 2024 • 6
General Preference Modeling with Preference Representations for Aligning Language Models Paper • 2410.02197 • Published Oct 3, 2024 • 9
Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis Paper • 2409.20059 • Published Sep 30, 2024 • 16
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages Paper • 2410.01036 • Published Oct 1, 2024 • 15
FactAlign: Long-form Factuality Alignment of Large Language Models Paper • 2410.01691 • Published Oct 2, 2024 • 9