CanvasMAR: Improving Masked Autoregressive Video Generation With Canvas
arXiv:2510.13669v1 Announce Type: cross Abstract: Masked autoregressive models (MAR) have recently emerged as a powerful paradigm for image and video…
AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
arXiv:2510.11496v2 Announce Type: replace-cross Abstract: In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet…
Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis
arXiv:2510.12642v1 Announce Type: cross Abstract: A growing trend in modern data analysis is the integration of data management with learning,…
Reasoning Pattern Matters: Learning to Reason without Human Rationales
arXiv:2510.12643v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm,…
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
arXiv:2510.11683v2 Announce Type: replace-cross Abstract: A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies…
AI Agents for the Dhumbal Card Game: A Comparative Study
arXiv:2510.11736v1 Announce Type: new Abstract: This study evaluates Artificial Intelligence (AI) agents for Dhumbal, a culturally significant multiplayer card game…
ChoirRec: Semantic User Grouping via LLMs for Conversion Rate Prediction of Low-Activity Users
arXiv:2510.09393v2 Announce Type: replace-cross Abstract: Accurately predicting conversion rates (CVR) for low-activity users remains a fundamental challenge in large-scale e-commerce…
PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities
arXiv:2510.11110v1 Announce Type: cross Abstract: Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints…
video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory
arXiv:2510.11129v1 Announce Type: cross Abstract: Continuous, high-frame-rate, high-resolution processing of long video streams is critical for future AI agents, yet…
SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
arXiv:2510.09541v2 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due…