#adaptive-computation News & Analysis

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

5 articles

AIBullisharXiv – CS AI · 4d ago7/10

🧠

When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning

Researchers present AVIC, an adaptive framework that optimizes when and how much multimodal language models should use world models for visual imagination during spatial reasoning tasks. The system learns to selectively invoke visual imagination only when necessary, reducing computational costs while matching or exceeding performance of fixed imagination strategies and proprietary baselines like GPT-4o.

🧠 GPT-4

AIBullisharXiv – CS AI · May 97/10

🧠

Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production

Researchers propose Catch Your Breath (CYB), a novel training method that enables AI models to dynamically control the number of computational steps used for processing inputs through <pause> tokens. The approach outperforms standard cross-entropy training by allowing models to signal when they need additional processing time, improving performance metrics like perplexity without increasing computational overhead.

🏢 Perplexity

AINeutralarXiv – CS AI · May 296/10

🧠

CosmicFish-HRM: Adaptive Reasoning via Hierarchical Recurrent Mechanisms in Compact Language Models

Researchers introduce CosmicFish-HRM, a compact language model that uses a Hierarchical Reasoning Module to dynamically adjust computational effort during inference based on input complexity. The approach challenges the assumption that larger models are necessary for advanced reasoning, suggesting adaptive computation depth could offer efficiency gains as model scale increases.

AIBullisharXiv – CS AI · Mar 176/10

🧠

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs

Researchers introduce AdaAnchor, a new AI reasoning framework that performs silent computation in latent space rather than generating verbose step-by-step reasoning. The system adaptively determines when to stop refining its internal reasoning process, achieving up to 5% better accuracy while reducing token generation by 92-93% and cutting refinement steps by 48-60%.

AIBullisharXiv – CS AI · Mar 37/105

🧠

DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks

Researchers introduce DynaMoE, a new Mixture-of-Experts framework that dynamically activates experts based on input complexity and uses adaptive capacity allocation across network layers. The system achieves superior parameter efficiency compared to static baselines and demonstrates that optimal expert scheduling strategies vary by task type and model scale.