…AI-generated summary Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains. While recent invariant learning strategies and…
…Ziwen Zhao , Abstract Ψ-RAG addresses limitations in tree-based retrieval-augmented generation for cross-document multi-hop questions through a hierarchical abstract tree index and multi-granular retrieval agent. AI-generated…
…AI-generated summary A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes…
…AI-generated summary Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for…
…Existing editing methods typically rely on a 2D-lifting strategy , where individual views are edited independently and then lifted back into 3D space. This indirect pipeline often leads to blurry textures and…
…AI-generated summary Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the…
…However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and suboptimal inference latency. Existing acceleration methods either require costly retraining with architectural changes or suffer from severe…
…Length Inflation and Stabilization Strategies for Large Language Models (2026) Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe (2026) Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn…
…AI-generated summary Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decoder can instead retrieve directly from its own internal representations…
…AI-generated summary Distributed blackbox consensus optimization is a fundamental problem in multi-agent systems, where agents must improve a global objective using only local objective queries and limited neighbor communication. Existing…