HUAWEI Noah's Ark Lab

company

Verified

http://www.noahlab.com.hk/

AI & ML interests

Artificial Intelligence

Recent Activity

Egorgij21 submitted a paper about 1 month ago

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Egorgij21 submitted a paper about 1 month ago

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

Darcy0123 submitted a paper about 2 months ago

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing

View all activity

Papers

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

A Geometric Account of Activation Steering through Angle-Norm Decomposition

View all Papers

submitted 2 papers to Daily Papers about 1 month ago

A Geometric Account of Activation Steering through Angle-Norm Decomposition

Paper • 2606.06735 • Published Jun 4 • 27

Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders

Paper • 2606.07473 • Published Jun 5 • 15

submitted a paper to Daily Papers about 2 months ago

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing

Paper • 2606.01804 • Published Jun 3 • 1

authored a paper about 2 months ago

LVSA: Training-Free Sparse Attention for Long Video Diffusion

Paper • 2605.31057 • Published May 29 • 14

submitted a paper to Daily Papers 4 months ago

Do World Action Models Generalize Better than VLAs? A Robustness Study

Paper • 2603.22078 • Published Apr 1 • 8

submitted a paper to Daily Papers 5 months ago

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published Feb 4 • 63

submitted a paper to Daily Papers 5 months ago

Vision Transformer Finetuning Benefits from Non-Smooth Components

Paper • 2602.06883 • Published Feb 6 • 4

submitted 2 papers to Daily Papers 6 months ago

An Empirical Study of World Model Quantization

Paper • 2602.02110 • Published Feb 2 • 5

Diffusion In Diffusion: Reclaiming Global Coherence in Semi-Autoregressive Diffusion

Paper • 2601.13599 • Published Jan 20 • 7

submitted a paper to Daily Papers 7 months ago

VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse

Paper • 2512.14531 • Published Dec 16, 2025 • 16

authored 7 papers 10 months ago

Tree-OPO: Off-policy Monte Carlo Tree-Guided Advantage Optimization for Multistep Reasoning

Paper • 2509.09284 • Published Sep 11, 2025 • 2

Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning

Paper • 2312.14878 • Published Dec 22, 2023 • 16

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning

Paper • 2406.19741 • Published Jun 28, 2024 • 60

Mixture of Attentions For Speculative Decoding

Paper • 2410.03804 • Published Oct 4, 2024

Almost Surely Safe Alignment of Large Language Models at Inference-Time

Paper • 2502.01208 • Published Feb 3, 2025 • 11

Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving

Paper • 2507.02726 • Published Jul 3, 2025 • 14

Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective

Paper • 2509.22921 • Published Sep 26, 2025 • 12

updated a dataset 12 months ago

huawei-noah/CHARP

Updated Jul 24, 2025 • 16 • 1

in huawei-noah/human_rank_eval over 1 year ago

Are these votes really reliable indicators?

#3 opened over 1 year ago by

in huawei-noah/human_rank_eval over 1 year ago

Are these votes really reliable indicators?

#3 opened over 1 year ago by