#autoregressive-generation News & Analysis

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

4 articles

AINeutralarXiv – CS AI · Jun 106/10

🧠

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

Researchers propose CPPO (Cumulative Prefix-divergence Policy Optimization), a new reinforcement learning method that improves upon standard PPO approaches for LLM training by accounting for position-dependent effects and cumulative policy divergence. The method uses position-weighted thresholds and prefix budgets to better regulate token-level deviations during autoregressive generation, showing improved training stability and reasoning accuracy across model scales.

AINeutralarXiv – CS AI · May 126/10

🧠

APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation

Researchers propose Adaptive Path-Contrastive Decoding (APCD), a multi-path decoding framework designed to reduce hallucinations in large language models by intelligently branching token generation paths based on entropy levels and controlling interactions between diverging prediction trajectories. The method demonstrates improved factual accuracy across eight benchmarks while maintaining computational efficiency.

AINeutralarXiv – CS AI · May 116/10

🧠

Discovering Learning-Friendly Generation Orders for Sequential Computation

Researchers have developed an automated method to discover optimal generation orders for sequential computation tasks, using loss profiling to evaluate candidate orders efficiently. The technique successfully raises success rates from ~10% to ~100% on order-sensitive tasks and rediscovers known efficient patterns like reverse-digit ordering for multiplication.

AINeutralarXiv – CS AI · Apr 146/10

🧠

Learning World Models for Interactive Video Generation

Researchers propose Video Retrieval Augmented Generation (VRAG) to address fundamental challenges in interactive world models for long-form video generation, specifically tackling compounding errors and spatiotemporal incoherence. The work establishes that autoregressive video generation inherently struggles with error accumulation, while explicit global state conditioning significantly improves long-term consistency and interactive planning capabilities.