arXiv subjects

Cheng Zhong

Publications and source records attributed to Cheng Zhong.

At least 19 recordsLinked to original sources

arXiv2026

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The flagship M2 contains 229.9B total parameters with only 9.8B activated per token. Designed end-to-end for agentic deployment, the M2 series rests on three components: (i) agent-driven data pipelines producing large-scale, verifiable trajectories across agentic coding and agentic cowork, each grounded in an executable workspace and an artifact-aligned reward; (ii) Forge, a scalable agent-native RL system that adapts to long-horizon agent trajectories, paired with windowed-FIFO scheduling, prefix-tree merging, inference optimization, and a clean training-inference-agent decoupling that supports both white-box and black-box agents; (iii) the latest M2.7 checkpoint takes an early step toward self-evolution -- autonomously debugging training runs and modifying its own scaffold. Across M2 through M2.7, this combination translates a mini-activation footprint into frontier-tier performance on agentic coding, deep search, office-task, and reasoning benchmarks.

cs.AI↗

arXiv2026

EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking

Egocentric video understanding is inherently complex due to the dynamic 4D nature of the environment, where camera motion and object displacements necessitate a continuous re-evaluation of spatial relations. In this work, we target a suite of under-explored egocentric 4D reasoning tasks, including fixture interaction counting, viewpoint-relative fixture location, object movement itinerary tracking, and stationary object localization, that require fundamentally different cognitive operations: spatial anchoring, temporal tracking, and duration reasoning. We observe that these structural differences make task-agnostic approaches insufficient: generic Chain-of-Thought methods lack task-appropriate reasoning primitives, and uniform reinforcement learning actively destabilizes performance on spatial tasks. To address this, we propose EgoReasoner, a two-stage framework that aligns both the reasoning scaffold and the reward signal to each task's cognitive structure. In the first stage, Task-Adaptive Thinking Templates guide the synthesis of structured CoT traces that teach the model to reason adaptively across task types via supervised fine-tuning. In the second stage, task-aware reward functions verify entity grounding, temporal alignment, and task-adaptive logical consistency, selectively strengthening each reasoning pathway via reinforcement fine-tuning with GRPO. Our 3B-parameter model, trained on only 16K samples, achieves 37.5% average accuracy on the challenging HD-EPIC benchmark, surpassing Qwen2.5-VL-7B (25.7%) by over 10 points.

cs.CV↗

arXiv2026

ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search

In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static multimodal settings. Open-domain video shot retrieval, which involves richer temporal structure and more complex semantics, still lacks systematic benchmarks and analysis. To fill this gap, we introduce ShotFinder, a benchmark that formalizes editing requirements as keyframe-oriented shot descriptions and introduces five types of controllable single-factor constraints: Temporal order, Color, Visual style, Audio, and Resolution. We curate 1,210 high-quality samples from YouTube across 20 thematic categories, using large models for generation with human verification. Based on the benchmark, we propose ShotFinder, a text-driven three-stage retrieval and localization pipeline: (1) query expansion via video imagination, (2) candidate video retrieval with a search engine, and (3) description-guided temporal localization. Experiments on multiple closed-source and open-source models reveal a significant gap to human performance, with clear imbalance across constraints: temporal localization is relatively tractable, while color and visual style remain major challenges. These results reveal that open-domain video shot retrieval is still a critical capability that multimodal large models have yet to overcome.

cs.CV↗

arXiv2026

AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent

Lossless compression has made significant advancements in Genomics Data (GD) storage, sharing and management. Current learning-based methods are non-evolvable with problems of low-level compression modeling, limited adaptability, and user-unfriendly interface. To this end, we propose AgentGC, the first evolutionary Agent-based GD Compressor, consisting of 3 layers with multi-agent named Leader and Worker. Specifically, the 1) User layer provides a user-friendly interface via Leader combined with LLM; 2) Cognitive layer, driven by the Leader, integrates LLM to consider joint optimization of algorithm-dataset-system, addressing the issues of low-level modeling and limited adaptability; and 3) Compression layer, headed by Worker, performs compression & decompression via a automated multi-knowledge learning-based compression framework. On top of AgentGC, we design 3 modes to support diverse scenarios: CP for compression-ratio priority, TP for throughput priority, and BM for balanced mode. Compared with 14 baselines on 9 datasets, the average compression ratios gains are 16.66%, 16.11%, and 16.33%, the throughput gains are 4.73x, 9.23x, and 9.15x, respectively.

cs.AI↗

arXiv2025

Do MLLMs Really Understand the Charts?

Although Multimodal Large Language Models (MLLMs) have demonstrated increasingly impressive performance in chart understanding, most of them exhibit alarming hallucinations and significant performance degradation when handling non-annotated charts. We argue that current MLLMs rely largely on visual recognition rather than visual reasoning to interpret the charts, and visual estimation of numerical values is one of the most fundamental capabilities in chart understanding that require complex visual reasoning. To prove this, we introduce ChartVRBench, a benchmark meticulously designed to isolate and evaluate visual reasoning ability in chart understanding. Furthermore, we propose ChartVR-3B/7B trained with a novel Visual Reasoning Reinforcement Finetuning (VR-RFT) strategy to strengthen genuine chart visual reasoning abilities. Extensive experiments show that ChartVR achieves superior performance on ChartVRBench, outperforming even powerful proprietary models. Moreover, the visual reasoning skills cultivated by the proposed VR-RFT demonstrate strong generalization, leading to significant performance gains across a diverse suite of public chart understanding benchmarks. The code and dataset will be publicly available upon publication.

cs.CL↗

arXiv2025

PMKLC: Parallel Multi-Knowledge Learning-based Lossless Compression for Large-Scale Genomics Database

Learning-based lossless compressors play a crucial role in large-scale genomic database backup, storage, transmission, and management. However, their 1) inadequate compression ratio, 2) low compression \& decompression throughput, and 3) poor compression robustness limit their widespread adoption and application in both industry and academia. To solve those challenges, we propose a novel \underline{P}arallel \underline{M}ulti-\underline{K}nowledge \underline{L}earning-based \underline{C}ompressor (PMKLC) with four crucial designs: 1) We propose an automated multi-knowledge learning-based compression framework as compressors' backbone to enhance compression ratio and robustness; 2) we design a GPU-accelerated ($s$,$k$)-mer encoder to optimize compression throughput and computing resource usage; 3) we introduce data block partitioning and Step-wise Model Passing (SMP) mechanisms for parallel acceleration; 4) We design two compression modes PMKLC-S and PMKLC-M to meet the complex application scenarios, where the former runs on a resource-constrained single GPU and the latter is multi-GPU accelerated. We benchmark PMKLC-S/M and 14 baselines (7 traditional and 7 leaning-based) on 15 real-world datasets with different species and data sizes. Compared to baselines on the testing datasets, PMKLC-S/M achieve the average compression ratio improvement up to 73.609\% and 73.480\%, the average throughput improvement up to 3.036$\times$ and 10.710$\times$, respectively. Besides, PMKLC-S/M also achieve the best robustness and competitive memory cost, indicating its greater stability against datasets with different probability distribution perturbations, and its strong ability to run on memory-constrained devices.

cs.LG↗

arXiv2025

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

We introduce EvaLearn, a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks, a critical, yet underexplored aspect of model potential. EvaLearn contains 648 challenging problems across six task types, grouped into 182 sequences, each sequence dedicated to one task type. Diverging from most existing benchmarks that evaluate models in parallel, EvaLearn requires models to solve problems sequentially, allowing them to leverage the experience gained from previous solutions. EvaLearn provides five comprehensive automated metrics to evaluate models and quantify their learning capability and efficiency. We extensively benchmark nine frontier models and observe varied performance profiles: some models, such as Claude-3.7-sonnet, start with moderate initial performance but exhibit strong learning ability, while some models struggle to benefit from experience and may even show negative transfer. Moreover, we investigate model performance under two learning settings and find that instance-level rubrics and teacher-model feedback further facilitate model learning. Importantly, we observe that current LLMs with stronger static abilities do not show a clear advantage in learning capability across all tasks, highlighting that EvaLearn evaluates a new dimension of model performance. We hope EvaLearn provides a novel evaluation perspective for assessing LLM potential and understanding the gap between models and human capabilities, promoting the development of deeper and more dynamic evaluation approaches. All datasets, the automatic evaluation framework, and the results studied in this paper are available at the GitHub repository.

cs.CL↗

arXiv2025

Intraday Functional PCA Forecasting of Cryptocurrency Returns

We study the Functional PCA (FPCA) forecasting method in application to functions of intraday returns on Bitcoin. We show that improved interval forecasts of future return functions are obtained when the conditional heteroscedasticity of return functions is taken into account. The Karhunen-Loeve (KL) dynamic factor model is introduced to bridge the functional and discrete time dynamic models. It offers a convenient framework for functional time series analysis. For intraday forecasting, we introduce a new algorithm based on the FPCA applied by rolling, which can be used for any data observed continuously 24/7. The proposed FPCA forecasting methods are applied to return functions computed from data sampled hourly and at 15-minute intervals. Next, the functional forecasts evaluated at discrete points in time are compared with the forecasts based on other methods, including machine learning and a traditional ARMA model. The proposed FPCA-based methods perform well in terms of forecast accuracy and outperform competitors in terms of directional (sign) of return forecasts at fixed points in time.

econ.EM↗

arXiv2025

CODA: Repurposing Continuous VAEs for Discrete Tokenization

Discrete visual tokenizers transform images into a sequence of tokens, enabling token-based visual generation akin to language models. However, this process is inherently challenging, as it requires both compressing visual signals into a compact representation and discretizing them into a fixed set of codes. Traditional discrete tokenizers typically learn the two tasks jointly, often leading to unstable training, low codebook utilization, and limited reconstruction quality. In this paper, we introduce \textbf{CODA}(\textbf{CO}ntinuous-to-\textbf{D}iscrete \textbf{A}daptation), a framework that decouples compression and discretization. Instead of training discrete tokenizers from scratch, CODA adapts off-the-shelf continuous VAEs -- already optimized for perceptual compression -- into discrete tokenizers via a carefully designed discretization process. By primarily focusing on discretization, CODA ensures stable and efficient training while retaining the strong visual fidelity of continuous VAEs. Empirically, with $\mathbf{6 \times}$ less training budget than standard VQGAN, our approach achieves a remarkable codebook utilization of 100% and notable reconstruction FID (rFID) of $\mathbf{0.43}$ and $\mathbf{1.34}$ for $8 \times$ and $16 \times$ compression on ImageNet 256$\times$ 256 benchmark.

cs.CV↗

arXiv2024

MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively.

cs.CV↗

arXiv2024

LGFN: Lightweight Light Field Image Super-Resolution using Local Convolution Modulation and Global Attention Feature Extraction

Capturing different intensity and directions of light rays at the same scene Light field (LF) can encode the 3D scene cues into a 4D LF image which has a wide range of applications (i.e. post-capture refocusing and depth sensing). LF image super-resolution (SR) aims to improve the image resolution limited by the performance of LF camera sensor. Although existing methods have achieved promising results the practical application of these models is limited because they are not lightweight enough. In this paper we propose a lightweight model named LGFN which integrates the local and global features of different views and the features of different channels for LF image SR. Specifically owing to neighboring regions of the same pixel position in different sub-aperture images exhibit similar structural relationships we design a lightweight CNN-based feature extraction module (namely DGCE) to extract local features better through feature modulation. Meanwhile as the position beyond the boundaries in the LF image presents a large disparity we propose an efficient spatial attention module (namely ESAM) which uses decomposable large-kernel convolution to obtain an enlarged receptive field and an efficient channel attention module (namely ECAM). Compared with the existing LF image SR models with large parameter our model has a parameter of 0.45M and a FLOPs of 19.33G which has achieved a competitive effect. Extensive experiments with ablation studies demonstrate the effectiveness of our proposed method which ranked the second place in the Track 2 Fidelity & Efficiency of NTIRE2024 Light Field Super Resolution Challenge and the seventh place in the Track 1 Fidelity.

eess.IV↗

arXiv2024

DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization

Traditional cross-domain tasks, including domain adaptation and domain generalization, rely heavily on training model by source domain data. With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (ADG). However, current cross-domain datasets have many limitations, such as unrealistic domains, unclear domain definitions, and the inability to fine-grained domain decomposition, which drives us to establish a novel dataset DomainVerse for ADG. Benefiting from the introduced hierarchical definition of domain shifts, DomainVerse consists of about 0.5 million images from 390 fine-grained realistic domains. With the help of the constructed DomainVerse and VLMs, we propose two methods called Domain CLIP and Domain++ CLIP for tuning-free adaptive domain generalization. Extensive and comprehensive experiments demonstrate the significance of the dataset and the effectiveness of the proposed methods.

cs.CV↗

arXiv2023

Collaborative Weakly Supervised Video Correlation Learning for Procedure-Aware Instructional Video Analysis

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, procedural knowledge is critical for accurate correlation analyses on instructional videos. Nevertheless, current procedure-learning methods heavily rely on step-level annotations, which are costly and not scalable. To address this problem, we introduce a weakly supervised framework called Collaborative Procedure Alignment (CPA) for procedure-aware correlation learning on instructional videos. Our framework comprises two core modules: collaborative step mining and frame-to-step alignment. The collaborative step mining module enables simultaneous and consistent step segmentation for paired videos, leveraging the semantic and temporal similarity between frames. Based on the identified steps, the frame-to-step alignment module performs alignment between the frames and steps across videos. The alignment result serves as a measurement of the correlation distance between two videos. We instantiate our framework in two distinct instructional video tasks: sequence verification and action quality assessment. Extensive experiments validate the effectiveness of our approach in providing accurate and interpretable correlation analyses for instructional videos.

cs.CV↗

arXiv2023

Hierarchical Reinforcement Learning for Automatic Disease Diagnosis

Motivation: Disease diagnosis oriented dialogue system models the interactive consultation procedure as Markov Decision Process and reinforcement learning algorithms are used to solve the problem. Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making. This strategy works well in the simple scenario when the action space is small, however, its efficiency will be challenged in the real environment. Inspired by the offline consultation process, we propose to integrate a hierarchical policy structure of two levels into the dialogue systemfor policy learning. The high-level policy consists of amastermodel that is responsible for triggering a low-levelmodel, the lowlevel policy consists of several symptom checkers and a disease classifier. The proposed policy structure is capable to deal with diagnosis problem including large number of diseases and symptoms. Results: Experimental results on three real-world datasets and a synthetic dataset demonstrate that our hierarchical framework achieves higher accuracy and symptom recall in disease diagnosis compared with existing systems. We construct a benchmark including datasets and implementation of existing algorithms to encourage follow-up researches. Availability: The code and data is available from https://github.com/FudanDISC/DISCOpen-MedBox-DialoDiagnosis Contact: 21210980124@m.fudan.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

cs.AI↗

arXiv2023

Secondary frequency control of islanded microgrid considering wind and solar stochastics

This paper proposed a model predictive control (MPC) secondary frequency control method considering wind and solar power generation stochastics. The extended state-space matrix including unknown stochastic power disturbance is established, and a Kalman filter is used to observe the unknown disturbance. The maximum available power of wind and solar DGs is estimated for establishing real-time variable constraints that prevent DGs output power from exceeding the limits. Through setting proper weight coefficients, wind and photovoltaic DGs are given priority to participate in secondary frequency control. The distributed restorative power of each DG is obtained by solving the quadratic programming (QP) optimal problem with variable constraints. Finally, a microgrid simulation model including multiple PV and wind DGs is built and performed in various scenarios compared to the traditional secondary frequency control method. The simulation results validated that the proposed method can enhance the frequency recovery speed and reduce the frequency deviation, especially in severe photovoltaic and wind fluctuations scenarios.

eess.SY↗

arXiv2023

DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation

We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonstrate the effectiveness of the proposed model in bridging the gap between general language models and real-world medical consultation. Additionally, we release the constructed dataset and model weights to further contribute to research and development. Further details and resources can be found at https://github.com/FudanDISC/DISC-MedLLM

cs.CL↗

arXiv2023

Model predictive control strategy in waked wind farms for optimal fatigue loads

With the rapid growth of wind power penetration, wind farms (WFs) are required to implement frequency regulation that active power control to track a given power reference. Due to the wake interaction of the wind turbines (WTs), there is more than one solution to distributing power reference among the operating WTs, which can be exploited as an optimization problem for the second goal, such as fatigue load alleviation. In this paper, a closed-loop model predictive controller is developed that minimizes the wind farm tracking errors, the dynamical fatigue load, and and the load equalization. The controller is evaluated in a mediumfidelity model. A 64 WTs simulation case study is used to demonstrate the control performance for different penalty factor settings. The results indicated the WF can alleviate dynamical fatigue load and have no significant impact on power tracking. However, the uneven load distribution in the wind turbine system poses challenges for maintenance. By adding a trade-off between the load equalization and dynamical fatigue load, the load differences between WTs are significantly reduced, while the dynamical fatigue load slightly increases when selecting a proper penalty factor.

eess.SY↗

arXiv2022

A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets

In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience. In this article, we propose two frameworks to support automatic medical consultation, namely doctor-patient dialogue understanding and task-oriented interaction. We create a new large medical dialogue dataset with multi-level finegrained annotations and establish five independent tasks, including named entity recognition, dialogue act classification, symptom label inference, medical report generation and diagnosis-oriented dialogue policy. We report a set of benchmark results for each task, which shows the usability of the dataset and sets a baseline for future studies. Both code and data is available from https://github.com/lemuria-wchen/imcs21.

cs.CL↗