Skip to content
Papers.

Native Audio-Visual Alignment for Generation research paper by Baidu, 2026

Baidu · May 28, 2026 · Alignment and safety · 6 citations · 31 upvotes · unverified

Read on arXiv

What it shows

NAVA enables joint audio-video generation with improved synchronization and controllability through native audio-visual alignment and context-conditioned denoising.

UnverifiedHugging Face's summary; not yet checked by hand.

More from Baidu

All 4
PaperCitations
Unlimited OCR WorksUnlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.Inference and efficiency · Jun 2026 · Unverified6
SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video EditingSAMA presents a factorized approach to video editing that separates semantic anchoring from motion modeling, enabling instruction-guided edits with preserved motion through pre-trained motion restoration tasks and sparse anchor frame prediction.Alignment and safety · Mar 2026 · Unverified5
Qianfan-OCR: A Unified End-to-End Model for Document IntelligenceQianfan-OCR is a 4B-parameter vision-language model that unifies document parsing, layout analysis, and understanding while maintaining strong performance across multiple OCR benchmarks through its Layout-as-Thought mechanism.Retrieval and data · Mar 2026 · Unverified20

Other alignment and safety papers

Topic
PaperCitations
Training language models to follow instructions with human feedbackInstructGPT: fine-tuning on human feedback made a 1.3B model preferred over the 175B GPT-3.OpenAI · Mar 202224.3k
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelDPO aligns a model to human preferences with a simple classification loss, no reward model or RL loop.Stanford University · May 202310.6k
Constitutional AI: Harmlessness from AI FeedbackConstitutional AI trains a harmless assistant from AI feedback guided by a short list of written principles, not human harm labels.Anthropic · Dec 20223,721
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety TrainingModels trained with a hidden backdoor kept their deceptive behaviour through standard safety training.Anthropic · Jan 2024578
Alignment faking in large language modelsClaude 3 Opus sometimes went along with a training goal it disagreed with, to avoid being changed, without being told to.Anthropic · Dec 2024343
Why Language Models HallucinateModels hallucinate because training and benchmarks reward confident guessing over saying they do not know.OpenAI · Sep 2025331
About this paper
Authors
Longbin Ji, Guan Wang, Xuan Wei and 6 more
arXiv
2605.30073 · PDF
Venue
arXiv.org
Citations
6, 2 influential · Semantic Scholar
Upvotes
31 · Hugging Face
Code
github.com/ernie-research/NAVA
Lab
Baidu · on Companies · on Quarterly

Changes

What changed
Influential citationsfirst count: 2Sep 25, 2026
Citationsfirst count: 6Sep 25, 2026
New paperFound by the weekly scan, unverifiedSep 25, 2026

Sources: each lab's own papers and arXiv, with citation and upvote counts from Semantic Scholar and Hugging Face. One-line summaries are for orientation, not a substitute for the paper. Logos via logo.dev; trademarks belong to their owners.

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.