arXiv
Learning Process Rewards via Success Visitation Matching for Efficient RL
In many modern applications of reinforcement learning (RL), the natural reward for a task of interest is inherently s...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
TailorMind: Towards Preference-Aligned Multimodal Content Generation
Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly...
arXiv
Tapered Language Models
Modern language models, including transformer, recurrent, and memory-based variants, share a common chassis: a stack ...
arXiv
Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles
This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Ma...
arXiv
PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support
Mental health assessment commonly relies on isolated screening instruments or data-driven models that often lack inte...
arXiv
Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?
AdamW is the de facto optimizer for training large language models (LLMs), yet the theory behind it still lives mostl...
arXiv
AIR: Adaptive Interleaved Reasoning with Code in MLLMs
Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance multimodal large lang...
arXiv
Semantic Browsing: Controllable Diversity for Image Generation
Modern text-to-image models excel in visual fidelity and prompt adherence. However, this strict adherence comes at th...
arXiv
CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation
Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipula...
HuggingFace
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene...
HuggingFace
Self-Compacting Language Model Agents
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent genera...
HuggingFace
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Latent action pretraining learns representations of visual change from pairs of observations, but existing methods ty...