Chenj

Tsuchen's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

SEAP: Training-free Sparse Expert Activation Pruning Unlock the Brainpower of Large Language Models

Paper • 2503.07605 • Published 4 days ago • 63

upvoted a paper 26 days ago

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

Paper • 2502.08946 • Published 30 days ago • 184

upvoted 18 papers 27 days ago

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

Old Optimizer, New Norm: An Anthology

Paper • 2409.20325 • Published Sep 30, 2024 • 4

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

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

Paper • 2409.18111 • Published Sep 26, 2024 • 7

Quantifying Generalization Complexity for Large Language Models

Paper • 2410.01769 • Published Oct 2, 2024 • 14

HelpSteer2-Preference: Complementing Ratings with Preferences

Paper • 2410.01257 • Published Oct 2, 2024 • 23

Selective Aggregation for Low-Rank Adaptation in Federated Learning

Paper • 2410.01463 • Published Oct 2, 2024 • 19

ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation

Paper • 2410.01731 • Published Oct 2, 2024 • 17