CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks
Paper • 2610.15327 • Published • 10
AI & ML interests
None defined yet.
Recent Activity
View all activity
timcuhk
submitted 2
papers to Daily Papers 3 days ago
timcuhk
authored 10
papers 4 days ago
SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs
Paper • 2608.27783 • Published
Auditing generative audio calls for known-task audio-llm evaluation
Paper • 2608.27817 • Published
AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTS
Paper • 2608.22186 • Published
VoxReason: Auditing Source-Grounded Speech Plans Before Synthesis
Paper • 2609.03203 • Published
From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection
Paper • 2609.08899 • Published
Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study
Paper • 2609.26823 • Published
When Does a Spoken Agent Have Enough Evidence to Act? The PACT-SLM Contract Test
Paper • 2609.38232 • Published
Controlled Acquisition and Abstention in Three-Channel Score Conflicts
Paper • 2610.10808 • Published • 7
Effective and Efficient Mixed Precision Quantization of Speech Foundation Models
Paper • 2501.03643 • Published
A Survey of Reasoning with Foundation Models
Paper • 2312.11562 • Published • 1
roedoejet
updated a
Space 6 months ago
roedoejet
updated a
model about 1 year ago
roedoejet
published a
model about 1 year ago
roedoejet
published a
Space over 1 year ago
roedoejet
updated a
model over 1 year ago