6 citations · 9 across the 21 of their papers we have counts for
22 papers
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Lei Yang, Mengyin Liu, Jia Wang +9
We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while r…
DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale
Jialiang Huang, Hongxuan Tang, Jingchang Chen +128
Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools,…
MentalThink: Shaping Thoughts in Mental SVG World
Kangheng Lin, Jisheng Yin, Dingming Li +11
We introduce MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal LLMs (MLLMs) with an executable mechanism for "mental" visualization. The core of MentalThink…
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception
Yana Wei, Hongbo Peng, Yanlin Lai +14
We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from h…
Step-Audio-R1.5 Technical Report
Yuxin Zhang, Xiangyu Tony Zhang, Daijiao Liu +16
Recent advancements in large audio language models have extended Chain-of-Thought (CoT) reasoning into the auditory domain, enabling models to tackle increasingly complex acoustic…
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Dinging Li, Yingxiu Zhao, Xinrui Cheng +16
Spatial reasoning over three-dimensional scenes is a core capability for embodied intelligence, yet continuous model improvement remains bottlenecked by the cost of geometric annot…
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering
Xiangfeng Wang, Hangyu Guo, Yanlin Lai +11
While model-based verifiers are essential for scaling Reinforcement Learning with Verifiable Rewards (RLVR), current outcome-centric verification paradigms primarily focus on the c…
R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging
Yanlin Lai, Mitt Huang, Hangyu Guo +11
Reinforcement Learning from Human Feedback (RLHF) remains indispensable for aligning large language models (LLMs) in subjective domains. To enhance robustness, recent work shifts t…
Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
Bao Shu, Yan Cai, Jianjian Sun +11
Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interaction offers a superio…
Step-Audio-R1 Technical Report
Fei Tian, Xiangyu Tony Zhang, Yuxin Zhang +14
Recent advances in reasoning models have demonstrated remarkable success in text and vision domains through extended chain-of-thought deliberation. However, a perplexing phenomenon…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Yana Wei, Liang Zhao, Jianjian Sun +15
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates…
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
En Yu, Kangheng Lin, Liang Zhao +11
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, ou…
Perception in Reflection
Yana Wei, Liang Zhao, Kangheng Lin +8
We present a perception in reflection paradigm designed to transcend the limitations of current large vision-language models (LVLMs), which are expected yet often fail to achieve p…
Unhackable Temporal Rewarding for Scalable Video MLLMs
En Yu, Kangheng Lin, Liang Zhao +8
In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the "anti-scaling law", where more data and larger models lead to worse performance. Th…
PerPO: Perceptual Preference Optimization via Discriminative Rewarding
Zining Zhu, Liang Zhao, Kangheng Lin +7
This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained mul…
Slow Perception: Let's Perceive Geometric Figures Step-by-step
Haoran Wei, Youyang Yin, Yumeng Li +6
Recently, "visual o1" began to enter people's vision, with expectations that this slow-thinking design can solve visual reasoning tasks, especially geometric math problems. However…
General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Haoran Wei, Chenglong Liu, Jinyue Chen +9
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper,…
Focus Anywhere for Fine-grained Multi-page Document Understanding
Chenglong Liu, Haoran Wei, Jinyue Chen +7
Modern LVLMs still struggle to achieve fine-grained document understanding, such as OCR/translation/caption for regions of interest to the user, tasks that require the context of t…
OneChart: Purify the Chart Structural Extraction via One Auxiliary Token
Jinyue Chen, Lingyu Kong, Haoran Wei +6
Chart parsing poses a significant challenge due to the diversity of styles, values, texts, and so forth. Even advanced large vision-language models (LVLMs) with billions of paramet…
Self-Supervised Visual Preference Alignment
Ke Zhu, Zheng Ge, Liang Zhao +1
This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original…
Small Language Model Meets with Reinforced Vision Vocabulary
Haoran Wei, Lingyu Kong, Jinyue Chen +6
Playing Large Vision Language Models (LVLMs) in 2023 is trendy among the AI community. However, the relatively large number of parameters (more than 7B) of popular LVLMs makes it d…