#adaptive-methods News & Analysis

4 articles tagged with #adaptive-methods. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AIBullisharXiv – CS AI · May 126/10

🧠

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models

Researchers introduce COAST, a novel pruning framework for vision-language models that reduces visual tokens by 77.8% while maintaining 98.64% performance and achieving 2.15x speedup. Unlike existing methods that discard low-attention tokens, COAST uses adaptive semantic routing to preserve contextually essential information, preventing 'Visual Aphasia'—a failure mode where models lose visual grounding.

AIBullisharXiv – CS AI · May 116/10

🧠

Revisiting Adam for Streaming Reinforcement Learning

Researchers challenge the conventional wisdom that deep reinforcement learning requires replay buffers by demonstrating that classical update methods like C51 perform competitively in streaming online settings when paired with proper optimization techniques. The study identifies two critical properties—bounded objective derivatives and variance-adjusted weight updates—as essential for stable learning, leading to a new algorithm called Adaptive Q(λ) that substantially outperforms existing streaming approaches.

AINeutralarXiv – CS AI · May 116/10

🧠

A Rod Flow Model for Adam at the Edge of Stability

Researchers extend rod flow modeling to Adam and other adaptive gradient methods, enabling more accurate continuous-time analysis of optimizer behavior at the edge of stability. This advancement bridges a gap in theoretical understanding of momentum-based optimization algorithms critical to modern deep learning.

AIBullisharXiv – CS AI · Apr 206/10

🧠

Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

Researchers propose Adaptive Entropy Regularization (AER), a dynamic framework that addresses policy entropy collapse in LLM reinforcement learning by adjusting exploration intensity based on task difficulty. The method improves upon fixed entropy regularization approaches, demonstrating consistent gains in mathematical reasoning benchmarks while maintaining balanced exploration-exploitation tradeoffs.