Tag
The paper introduces Continuous Audio Thinking (CoAT), a framework that equips large audio language models with a continuous latent workspace to organize acoustic information before generating textual responses, improving performance on audio reasoning, understanding, and transcription tasks without additional decoding cost.
AgentPSO is a particle-swarm-inspired framework that evolves multi-agent reasoning skills by treating agents as particles whose states are natural-language skills. It improves performance on reasoning benchmarks without updating the backbone language model parameters.
This paper introduces a quantitative framework and visualization tool called 'Narrative Landscape' to map and compare the narrative dispositions and stability of frontier LLMs.
This paper proposes LMO-IGT, a new class of stochastic optimization methods that accelerates convergence using implicit gradient transport while maintaining a single-gradient-per-iteration structure. It introduces a unified theoretical framework and demonstrates improved performance over existing LMO-based optimizers like Muon.