Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
Paper • 2603.14636 • Published • 1
AI & ML interests
None defined yet.
Recent Activity
zenyn
submitted a
paper to Daily Papers 1 day ago
zenyn
authored 3
papers 1 day ago
A Preliminary Exploration with GPT-4o Voice Mode
Paper • 2502.09940 • Published
MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
Paper • 2603.09714 • Published
Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
Paper • 2603.14636 • Published • 1
kehanlu
updated a
dataset about 2 months ago
kehanlu
updated a
model about 2 months ago
dlion168
submitted a
paper to Daily Papers 2 months ago
zenyn
authored 2
papers 5 months ago
huckiyang
authored 11
papers 5 months ago
Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting
Paper • 2309.15649 • Published • 1
Conditional Modeling Based Automatic Video Summarization
Paper • 2311.12159 • Published • 1
Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue
Paper • 2312.15316 • Published
Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification
Paper • 2312.14378 • Published
GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators
Paper • 2402.06894 • Published • 1
Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
Paper • 2409.20007 • Published • 1
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Paper • 2411.05361 • Published • 5
Towards Neural Scaling Laws for Time Series Foundation Models
Paper • 2410.12360 • Published
Plan2Align: Predictive Planning Based Test-Time Preference Alignment in Paragraph-Level Machine Translation
Paper • 2502.20795 • Published
Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition
Paper • 2409.09785 • Published
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Paper • 2507.02768 • Published • 19