2 citations · 4 across the 17 of their papers we have counts for
9 papers · 1 filter
AdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum Learning
Sida Li, Yuanxin Liu, Linli Yao +4
While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored. Visual…
PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention
Kunming Shao, Jierun Chen, Yanli Wang +4
At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by memory bandwidth. Sparse at…
GPTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation
Ruikang Liu, Haoli Bai, Yuxuan Sun +8
Post-training quantization (PTQ) is a practical approach to reducing the memory and computational footprint of large language models (LLMs) without retraining. GPTQ-based methods h…
AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction
Ziqiang Cui, Han Shi, Bowei He +8
Multi-Token Prediction (MTP) has emerged as an effective paradigm that augments a shared Large Language Model backbone with auxiliary heads, training the model to predict several f…
Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget
Guoxuan Chen, Chufeng Xiao, Haoran Yang +30
We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising Base, Turbo, Edit, and Edit-Turbo variants. It delivers compet…
Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation
Yishuo Cai, Jiahui Liu, Yuanxin Liu +9
''Thinking with Images'' has emerged as an effective paradigm for fine-grained visual reasoning: by explicitly zooming into relevant regions and reasoning over crops, models can ac…
GRPO-VPS: Enhancing Group Relative Policy Optimization with Verifiable Process Supervision for Effective Reasoning
Jingyi Wang, Lei Zhu, Tengjin Weng +8
Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Language Models (LLMs) by leveraging direct outcome verification instead of l…
What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
Keyu Lv, Manyi Zhang, Xiaobo Xia +6
Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training…
Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats
Manyi Zhang, Ji-Fu Li, Zhongao Sun +4
Microscaling Floating-Point (MXFP) has emerged as a promising low-precision format for large language models (LLMs). Despite various post-training quantization (PTQ) algorithms bei…