8 papers
How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining
Lin Chen, Bolin Ni, Qi Yang +6
Most modern multimodal large language models (MLLMs) build on a pretrained visual encoder that provides a strong visual prior. Encoder-free MLLMs instead learn visual representatio…
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Tencent Robotics X, HY Vision Team, : +20
We introduce HY-Embodied-0.5, a family of foundation models specifically designed for real-world embodied agents. To bridge the gap between general Vision-Language Models (VLMs) an…
Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding
Lin Chen, Bolin Ni, Qi Yang +5
Despite the remarkable capabilities of Multimodal Large Language Models (MLLMs), they still suffer from visual fading in long-context scenarios. Specifically, the attention to visu…
SSL: Sweet Spot Learning for Differentiated Guidance in Agentic Optimization
Jinyang Wu, Changpeng Yang, Yuhao Shen +9
Reinforcement learning with verifiable rewards has emerged as a powerful paradigm for training intelligent agents. However, existing methods typically employ binary rewards that fa…
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
Yi Zhang, Bolin Ni, Xin-Sheng Chen +7
Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SF…
R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning
Qi Yang, Bolin Ni, Shiming Xiang +3
Multimodal Large Language Models (MLLMs) equipped with step-by-step thinking capabilities have demonstrated remarkable performance on complex reasoning problems. However, this thin…
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation
Meng-Hao Guo, Jiajun Xu, Yi Zhang +14
Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmark…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…