MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce the MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1,464 videos with varying resolutions, aspect ratios, and durations, along with 2,000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2.5 Pro) achieves an accuracy of only 73.7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce SuperRS-VQA (avg. 8,376$\times$8,376) and HighRS-VQA (avg. 2,000$\times$1,912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e.g., ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: Background Token Pruning and Anchored Token Selection, to reduce the memory footprint while preserving key semantics.Integrating these techniques, we introduce GeoLLaVA-8K, the first RS-focused multimodal large language model capable of handling inputs up to 8K$\times$8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench.

Not All Correct Answers Are Equal: Why Your Distillation Source Matters

Distillation has emerged as a practical and effective approach to enhance the reasoning capabilities of open-source language models. In this work, we conduct a large-scale empirical study on reasoning data distillation by collecting verified outputs from three state-of-the-art teacher models-AM-Thinking-v1, Qwen3-235B-A22B, and DeepSeek-R1-on a shared corpus of 1.89 million queries. We construct three parallel datasets and analyze their distributions, revealing that AM-Thinking-v1-distilled data exhibits greater token length diversity and lower perplexity. Student models trained on each dataset are evaluated on reasoning benchmarks including AIME2024, AIME2025, MATH500, and LiveCodeBench. The AM-based model consistently achieves the best performance (e.g., 84.3 on AIME2024, 72.2 on AIME2025, 98.4 on MATH500, and 65.9 on LiveCodeBench) and demonstrates adaptive output behavior-producing longer responses for harder tasks and shorter ones for simpler tasks. These findings highlight the value of high-quality, verified reasoning traces. We release the AM-Thinking-v1 and Qwen3-235B-A22B distilled datasets to support future research on open and high-performing reasoning-oriented language models. The datasets are publicly available on Hugging Face\footnote{Datasets are available on Hugging Face: \href{https://huggingface.co/datasets/a-m-team/AM-Thinking-v1-Distilled}{AM-Thinking-v1-Distilled}, \href{https://huggingface.co/datasets/a-m-team/AM-Qwen3-Distilled}{AM-Qwen3-Distilled}.}.

AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale

We present AM-Thinking-v1, a 32B dense language model that advances the frontier of reasoning, embodying the collaborative spirit of open-source innovation. Outperforming DeepSeek-R1 and rivaling leading Mixture-of-Experts (MoE) models like Qwen3-235B-A22B and Seed1.5-Thinking, AM-Thinking-v1 achieves impressive scores of 85.3 on AIME 2024, 74.4 on AIME 2025, and 70.3 on LiveCodeBench, showcasing state-of-the-art mathematical and coding capabilities among open-source models of similar scale. Built entirely from the open-source Qwen2.5-32B base model and publicly available queries, AM-Thinking-v1 leverages a meticulously crafted post-training pipeline - combining supervised fine-tuning and reinforcement learning - to deliver exceptional reasoning capabilities. This work demonstrates that the open-source community can achieve high performance at the 32B scale, a practical sweet spot for deployment and fine-tuning. By striking a balance between top-tier performance and real-world usability, we hope AM-Thinking-v1 inspires further collaborative efforts to harness mid-scale models, pushing reasoning boundaries while keeping accessibility at the core of innovation. We have open-sourced our model on \href{https://huggingface.co/a-m-team/AM-Thinking-v1}{Hugging Face}.

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

Despite significant advances in long-context reasoning by large language models (LLMs), primarily through Online Reinforcement Learning (RL) methods, these approaches incur substantial computational costs and complexity. In contrast, simpler and more economical Offline RL methods remain underexplored. To address this gap, we investigate the effectiveness of Offline RL methods, specifically Direct Preference Optimization (DPO) and its length-desensitized variant LD-DPO, in enhancing the reasoning capabilities of LLMs. Extensive experiments across multiple reasoning benchmarks demonstrate that these simpler Offline RL methods substantially improve model performance, achieving an average enhancement of 3.3\%, with a particularly notable increase of 10.1\% on the challenging Arena-Hard benchmark. Furthermore, we analyze DPO's sensitivity to output length, emphasizing that increasing reasoning length should align with semantic richness, as indiscriminate lengthening may adversely affect model performance. We provide comprehensive descriptions of our data processing and training methodologies, offering empirical evidence and practical insights for developing more cost-effective Offline RL approaches.

DeepSTA: A Spatial-Temporal Attention Network for Logistics Delivery Timely Rate Prediction in Anomaly Conditions

Prediction of couriers' delivery timely rates in advance is essential to the logistics industry, enabling companies to take preemptive measures to ensure the normal operation of delivery services. This becomes even more critical during anomaly conditions like the epidemic outbreak, during which couriers' delivery timely rate will decline markedly and fluctuates significantly. Existing studies pay less attention to the logistics scenario. Moreover, many works focusing on prediction tasks in anomaly scenarios fail to explicitly model abnormal events, e.g., treating external factors equally with other features, resulting in great information loss. Further, since some anomalous events occur infrequently, traditional data-driven methods perform poorly in these scenarios. To deal with them, we propose a deep spatial-temporal attention model, named DeepSTA. To be specific, to avoid information loss, we design an anomaly spatio-temporal learning module that employs a recurrent neural network to model incident information. Additionally, we utilize Node2vec to model correlations between road districts, and adopt graph neural networks and long short-term memory to capture the spatial-temporal dependencies of couriers. To tackle the issue of insufficient training data in abnormal circumstances, we propose an anomaly pattern attention module that adopts a memory network for couriers' anomaly feature patterns storage via attention mechanisms. The experiments on real-world logistics datasets during the COVID-19 outbreak in 2022 show the model outperforms the best baselines by 12.11% in MAE and 13.71% in MSE, demonstrating its superior performance over multiple competitive baselines.

Learning to Estimate Package Delivery Time in Mixed Imbalanced Delivery and Pickup Logistics Services

Accurately estimating package delivery time is essential to the logistics industry, which enables reasonable work allocation and on-time service guarantee. This becomes even more necessary in mixed logistics scenarios where couriers handle a high volume of delivery and a smaller number of pickup simultaneously. However, most of the related works treat the pickup and delivery patterns on couriers' decision behavior equally, neglecting that the pickup has a greater impact on couriers' decision-making compared to the delivery due to its tighter time constraints. In such context, we have three main challenges: 1) multiple spatiotemporal factors are intricately interconnected, significantly affecting couriers' delivery behavior; 2) pickups have stricter time requirements but are limited in number, making it challenging to model their effects on couriers' delivery process; 3) couriers' spatial mobility patterns are critical determinants of their delivery behavior, but have been insufficiently explored. To deal with these, we propose TransPDT, a Transformer-based multi-task package delivery time prediction model. We first employ the Transformer encoder architecture to capture the spatio-temporal dependencies of couriers' historical travel routes and pending package sets. Then we design the pattern memory to learn the patterns of pickup in the imbalanced dataset via attention mechanism. We also set the route prediction as an auxiliary task of delivery time prediction, and incorporate the prior courier spatial movement regularities in prediction. Extensive experiments on real industry-scale datasets demonstrate the superiority of our method. A system based on TransPDT is deployed internally in JD Logistics to track more than 2000 couriers handling hundreds of thousands of packages per day in Beijing.

DeepDistill: Enhancing LLM Reasoning Capabilities via Large-Scale Difficulty-Graded Data Training

Although large language models (LLMs) have recently achieved remarkable performance on various complex reasoning benchmarks, the academic community still lacks an in-depth understanding of base model training processes and data quality. To address this, we construct a large-scale, difficulty-graded reasoning dataset containing approximately 3.34 million unique queries of varying difficulty levels and about 40 million distilled responses generated by multiple models over several passes. Leveraging pass rate and Coefficient of Variation (CV), we precisely select the most valuable training data to enhance reasoning capability. Notably, we observe a training pattern shift, indicating that reasoning-focused training based on base models requires higher learning rates for effective training. Using this carefully selected data, we significantly improve the reasoning capabilities of the base model, achieving a pass rate of 79.2\% on the AIME2024 mathematical reasoning benchmark. This result surpasses most current distilled models and closely approaches state-of-the-art performance. We provide detailed descriptions of our data processing, difficulty assessment, and training methodology, and have publicly released all datasets and methods to promote rapid progress in open-source long-reasoning LLMs. The dataset is available at: https://huggingface.co/datasets/a-m-team/AM-DeepSeek-Distilled-40M

Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability

Recent advancements in large language models (LLMs), such as DeepSeek-R1 and OpenAI-o1, have demonstrated the significant effectiveness of test-time scaling, achieving substantial performance gains across various benchmarks. These advanced models utilize deliberate "thinking" steps to systematically enhance answer quality. In this paper, we propose leveraging these high-quality outputs generated by reasoning-intensive models to improve less computationally demanding, non-reasoning models. We explore and compare methodologies for utilizing the answers produced by reasoning models to train and improve non-reasoning models. Through straightforward Supervised Fine-Tuning (SFT) experiments on established benchmarks, we demonstrate consistent improvements across various benchmarks, underscoring the potential of this approach for advancing the ability of models to answer questions directly.

Dual Boost-Driven Graph-Level Clustering Network

Graph-level clustering remains a pivotal yet formidable challenge in graph learning. Recently, the integration of deep learning with representation learning has demonstrated notable advancements, yielding performance enhancements to a certain degree. However, existing methods suffer from at least one of the following issues: 1. the original graph structure has noise, and 2. during feature propagation and pooling processes, noise is gradually aggregated into the graph-level embeddings through information propagation. Consequently, these two limitations mask clustering-friendly information, leading to suboptimal graph-level clustering performance. To this end, we propose a novel Dual Boost-Driven Graph-Level Clustering Network (DBGCN) to alternately promote graph-level clustering and filtering out interference information in a unified framework. Specifically, in the pooling step, we evaluate the contribution of features at the global and optimize them using a learnable transformation matrix to obtain high-quality graph-level representation, such that the model's reasoning capability can be improved. Moreover, to enable reliable graph-level clustering, we first identify and suppress information detrimental to clustering by evaluating similarities between graph-level representations, providing more accurate guidance for multi-view fusion. Extensive experiments demonstrated that DBGCN outperforms the state-of-the-art graph-level clustering methods on six benchmark datasets.