7 papers
Multi-Branch Policy Optimization for Multimodal Large Language Models
Shuai Lyu, Yuning Gong, Ruiling Gao +7
Group-based reinforcement learning methods for multimodal large language models typically rely on trajectory-level credit assignment that applies a single advantage to all tokens i…
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models
Glenn Jocher, Jing Qiu, Mengyu Liu +3
Real-time vision demands models that are accurate, efficient, and simple to deploy across diverse hardware. The YOLO family has become widely deployed for this reason, yet most YOL…
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
Yu Feng, Zhen Tian, Haoran Luo +8
Domain Incremental Learning is a critical scenario that requires models to continuously adapt to new data domains without retraining. However, domain shifts often cause severe perf…
CreBench: Human-Aligned Creativity Evaluation from Idea to Process to Product
Kaiwen Xue, Chenglong Li, Zhonghong Ou +10
Human-defined creativity is highly abstract, posing a challenge for multimodal large language models (MLLMs) to comprehend and assess creativity that aligns with human judgments. T…
TSVC:Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval
Shuai Lyu, Zijing Tian, Zhonghong Ou +5
Cross-modal retrieval maps data under different modality via semantic relevance. Existing approaches implicitly assume that data pairs are well-aligned and ignore the widely existi…
SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL
Shuai Lyu, Haoran Luo, Ripeng Li +6
Text-to-SQL (Text2SQL) aims to map natural language questions to executable SQL queries. Although large language models (LLMs) have driven significant progress, current approaches…