#residual-learning News & Analysis

2 articles tagged with #residual-learning. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Jun 86/10

🧠

Enhancing Video Representations with Spatiotemporal-Semantic Residual to Mitigate Hallucinations in Video Large Multimodal Models

Researchers introduce ViSSRes, an inference-time intervention method that reduces hallucinations in Video Large Multimodal Models by enhancing video representations through a lightweight MLP network. The approach achieves a 40.69% reduction in hallucination rates on LLaVA-NeXT-Video while improving video understanding by 18.36%, with minimal computational overhead during inference.

AINeutralarXiv – CS AI · May 286/10

🧠

SPAR: Support-Preserving Action Rectification

Researchers introduce SPAR (Support-Preserving Action Rectification), a new offline reinforcement learning method that addresses the fundamental tension between maximizing value and staying true to training data. By anchoring policy improvements to frozen behavior cloning and operating in residual space, SPAR achieves state-of-the-art results on D4RL benchmarks while maintaining data distribution fidelity.