arXiv subjects

Guangtao Zhai

Publications and source records attributed to Guangtao Zhai.

At least 55 records · Page 3Linked to original sources

arXiv2026

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discovery. We evaluate seven autonomous research (auto-research) agents under a unified protocol and seventeen native LLMs through the lightweight ResearchHarness. Current systems remain far from reliable re-discovery: the strongest autonomous agent, Claude Code, averages 21.5, and the strongest ResearchHarness LLM, Claude-Opus-4.7, averages 20.7, with an LLM frontier mean of only 26.5. Error analysis shows that failures concentrate in experimental protocol mismatch, evidence mismatch, and missing scientific core. ResearchClawBench provides a reproducible evaluation frontier for measuring progress toward autonomous scientific research.

cs.LG↗

arXiv2026

FUMO: Prior-Modulated Diffusion for Single Image Reflection Removal

Single image reflection removal (SIRR) is challenging in real scenes, where reflection strength varies spatially and reflection patterns are tightly entangled with transmission structures. This paper presents a diffusion model with prior modulation framework (FUMO) that introduces explicit priors for spatially adaptive conditioning and structurally faithful restoration. Two priors are extracted directly from the mixed image, an intensity prior that estimates spatial reflection severity and a high-frequency prior that captures detail-sensitive responses via multi-scale residual aggregation. We propose a coarse-to-fine training paradigm. In the first stage, these cues are combined to gate the conditional residual injections, focusing the conditioning on regions that are both reflection-dominant and structure-sensitive. In the second stage, a fine-grained refinement network corrects local misalignment and sharpens fine details in the image space. Experiments conducted on both standard benchmarks and challenging images in the wild demonstrate competitive quantitative results and consistently improved perceptual quality. The code is released at https://github.com/Lucious-Desmon/FUMO.

cs.CV↗

arXiv2026

DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble

We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images. The framework jointly predicts global, target, and background quality scores by ensembling two complementary pipelines: (1) SigLIP2 vision encoders with multi-task regression heads, and (2) a LoRA-adapted Qwen3.5-9B multimodal large language model for quality score regression. The final global quality prediction is obtained by arithmetically averaging the outputs of both pipelines. Our method achieves 2nd place in the challenge, demonstrating its effectiveness. The code is available at https://github.com/sunwei925/DroneIQA-VLE.

cs.CV↗

arXiv2026

Beyond Single Character: Evaluating MLLMs for Sentence-Level Oracle Bone Inscription Understanding

Existing AI-assisted oracle bone inscription (OBI) visual recognition and understanding studies mainly focus on character-level, ignoring the long-form textual coherence and contextual dependencies embedded in complete divination charges. Recently, the powerful visual perception capabilities of multimodal large language models (MLLMs) have opened new possibilities for OBI information processing. In this work, we introduce S-OBI, a novel benchmark for evaluating MLLMs in Sentence-level OBI understanding. Instead of using noisy and incomplete rubbings as the visual input, S-OBI synthesizes clear and standardized sentence-level OBI instances through glyph substitution and composition. According to 95 original rubbings with translations that have been identified, corrected, and verified by experts, we replace characters in the original rubbings with corresponding clean glyph samples sourced from existing OBI datasets while preserving the overall inscriptional structure and semantic organization. This mitigates the influence of low-level distortions and enables a more focused evaluation of sentence-level OBI understanding. Based on this, we design semantic matching, semantic slot extraction, and contextual reasoning tasks and obtain 695 question-answer pairs. Experiments reveal the inferiority of contemporary MLLMs on sentence-level OBI understanding. In particular, visual perception errors in unmasked regions propagate through the reasoning chain, leading to erroneous predictions for masked characters, which indicates that sentence-level OBI understanding in current models remains strongly dependent on character-level recognition. Overall, S-OBI provides a diagnostic benchmark for evaluating whether MLLMs can move beyond isolated character recognition toward structured inscription-level understanding.

cs.CV↗

arXiv2026

LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning

Low-light image enhancement algorithms (LIEAs) aim to improve the visibility of images captured under poor illumination. However, the enhancement process often introduces artifacts such as noise amplification, color shift, structural damage, and over-exposure, which degrade the perceptual quality of the enhanced images. Therefore, a reliable image quality assessment (IQA) metric for evaluating enhancement effects is of great importance for both the development of LIEAs and their practical applications. In this paper, we present \textbf{LEIQ-Assessor}, a multi-dimensional quality assessment model for low-light image enhancement based on multi-task learning, developed for the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. Specifically, our method leverages a pre-trained SigLIP2 Vision Transformer as the backbone and simultaneously predicts the overall Mean Opinion Score (MOS) together with six perceptual sub-attributes: lightness, color fidelity, noise level, exposure quality, naturalness, and content recovery. By jointly optimizing these correlated objectives via the PLCC loss, the shared representation captures richer quality-aware features than its single-task counterpart. Experiments on the MLE benchmark demonstrate that LEIQ-Assessor significantly outperforms existing no-reference IQA models and hand-crafted quality descriptors. Our method achieved second place in the QoMEX 2026 Grand Challenge on Low-light Enhanced Image Quality Assessment. The code is available at https://github.com/sunwei925/LEIQ-Assessor.

cs.CV↗

arXiv2026

LatentRevise: Learning from Zero-Hit Reasoning

Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by hard prompts on which correct trajectories have low probability, so sampling misses them within a practical budget and leaves the policy update with little useful signal. We frame such zero-hit prompts as RLVR's sampling frontier, where new reasoning behavior is most valuable yet least likely to be sampled. Importantly, failed rollouts can be informative: they expose where the model's reasoning went wrong. We introduce LatentRevise, a first-order latent revision method that recovers training signal for this zero-hit regime. Given a failed rollout and the gold answer as an anchor, LatentRevise optimizes the input embeddings of its reasoning prefix under two complementary gradients, moving the prefix away from the failed continuation and toward the gold answer. The optimization is constrained to the convex hull of the model's vocabulary embeddings, so each update moves the latent toward a real token embedding rather than an arbitrary feature direction. We find that continuations from the revised prefix lengthen, exhibit self-reflection, and reach correct answers missed by the original rollouts. Used as training data, these trajectories improve SFT and RLVR on math benchmarks over standard baselines.

cs.CL↗

arXiv2026

EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment

Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce EEmoDB, the largest image-evoked emotion understanding dataset to date. It features $5$ analysis dimensions spanning $5$ distinct task categories, facilitating comprehensive interpretation. Specifically, we compile $1.2M$ question-answering (QA) pairs (EEmoDB-QA) from $125K$ images via automated generation, alongside a $36K$ dataset (EEmoDB-Assess) curated from $25K$ images for fine-grained assessment. Furthermore, we propose EEmo-Logic, an all-in-one multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The dataset and code are available at https://github.com/workerred/EEmo-Logic.

cs.CV↗

arXiv2026

In-context Region-based Drag: Drag Any Region to Any Shape

Diffusion models have shown promise in drag-style editing. Previous works mainly focus on point-based drag, which is inherently ambiguous. This paper focuses on region-based drag and introduces a novel In-Context Region-based Drag (ICRDrag) method. Under the in-context learning framework, ICRDrag consumes a source image, a source region mask, and a target region mask, producing the target dragged image. Built upon the basic in-context learning model, we introduce two novel attention regularization: 1) image-mask attention consistency to ensure that a target region attends to similar source regions for image and mask modalities; 2) source-target attention correspondence to ensure the mutual correspondence between source and target regions. To facilitate region-based drag, we also construct Paired Region Dataset (PRD), a large-scale dataset with paired masks and images. Extensive experiments show that ICRDrag significantly outperforms existing methods in both quantitative metrics and user studies, achieving superior editing accuracy and visual fidelity. The dataset, code, and model are available at https://github.com/bcmi/ICRDrag-Region-Drag-Editing.

cs.CV↗

arXiv2026

DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment

Recent multimodal large language models (MLLMs) have shown promising performance on video quality assessment (VQA) tasks. However, adapting them to new scenarios remains expensive due to large-scale retraining and costly mean opinion score (MOS) annotations. In this paper, we argue that a pretrained MLLM already provides a useful perceptual prior for VQA, and that the main challenge is to efficiently calibrate this prior to the target MOS space. Based on this insight, we propose DPC-VQA, a decoupling perception and calibration framework for video quality assessment. Specifically, DPC-VQA uses a frozen MLLM to provide a base quality estimate and perceptual prior, and employs a lightweight calibration branch to predict a residual correction for target-scenario adaptation. This design avoids costly end-to-end retraining while maintaining reliable performance with lower training and data costs. Extensive experiments on both user-generated content (UGC) and AI-generated content (AIGC) benchmarks show that DPC-VQA achieves competitive performance against representative baselines, while using less than 2% of the trainable parameters of conventional MLLM-based VQA methods and remaining effective with only 20% of MOS labels. The code will be released upon publication.

cs.CV↗

arXiv2026

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon known as emergent misalignment. However, efficient methods for reversing such misalignment remain limited. In this work, we make two contributions. First, we identify sycophancy fine-tuning, i.e., training models to passively agree with users' incorrect opinions, as a previously underexplored driver of emergent misalignment, and show that it induces broad and severe misaligned behavior. Second, we propose Alignment Gating, an efficient method for reversing emergent misalignment that inserts learnable and controllable gates into the model during fine-tuning. Through fine-tuning, these gates learn to identify the internal representations responsible for unsafe responses. Thus, amplifying or suppressing these representations then exacerbates or mitigates EM, respectively. We further find that alignment gating module exhibits strong generalization: gating weights obtained from narrow-domain fine-tuning substantially suppress broad-domain misaligned behavior while preserving the model's general capabilities.

cs.CL↗

arXiv2026

LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models

Large-scale generative models have demonstrated remarkable capabilities across image generation and editing tasks. However, their performance in low-level vision tasks, which require pixel-wise control, remains insufficiently studied. To address this gap, we introduce \textbf{LL-Bench}, a comprehensive \textbf{Benchmark} for evaluating the capabilities of large-scale generative models on \textbf{L}ow-\textbf{L}evel vision tasks. The benchmark comprises 2,469 real-world degraded images covering 16 low-level degradation tasks, and 28,919 restored images produced by 10 state-of-the-art large-scale generative models and 21 conventional restoration models, which are annotated with 152,020 expert-level pairwise human preferences and 28,334 quality scores. Built upon LL-Bench, we present a systematic diagnosis that reveals the performance boundaries and unique failure modes of large-scale generative models across diverse low-level vision tasks, compared with conventional representative restoration approaches. Moreover, we investigate the effectiveness of current quality evaluation metrics on LL-Bench, which exhibit significant discrepancy with human ratings. To better align restored-image quality assessment with human preferences, we further propose \textbf{LL-Score}, an MLLM-based evaluator that captures both restoration quality and hallucination existence. Extensive experiments demonstrate that LL-score not only outperforms existing image quality assessment metrics, but also serves as a promising reward model for training generative models on low-level vision tasks.

cs.CV↗

arXiv2026

UniDial-EvalKit: A Unified Toolkit for Evaluating Multi-Faceted Conversational Abilities

Benchmarking large language models (LLMs) and agents in multi-turn interactive scenarios is essential for understanding their practical capabilities. However, existing evaluation protocols are highly heterogeneous, differing significantly in dataset formats, model interfaces, and evaluation pipelines, which severely impedes systematic comparison. In this work, we present UniDial-EvalKit (UDE), a unified evaluation toolkit for assessing interactive AI systems. The core contribution of UDE lies in its holistic unification: it standardizes heterogeneous data formats into a universal schema, streamlines complex evaluation pipelines through a modular architecture, and aligns metric calculations under a hierarchical scoring aggregation. It also supports efficient large-scale evaluation through parallel generation and scoring, as well as checkpoint resume to eliminate redundant computation. Leveraging UDE, we conduct an extensive evaluation across diverse multi-dimensional benchmarks. Our empirical analysis shows that no single system consistently outperforms others across all benchmarks, while current memory agents often fail to surpass full-context baselines. Further analyses highlight several future directions, including benchmark deduplication and more adaptive memory architectures.

cs.CL↗

arXiv2026

DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation

With the continued advancement of text-to-image (T2I) generation, producing high-quality images is becoming increasingly attainable; consequently, user demands are shifting toward images that better satisfy their specific requirements. As reward models play an increasingly important role in assessing whether generated images align with user preference, this trend introduces an important challenge for reward modeling: rather than relying solely on static and general evaluation dimensions, reward models should account for the task-relevant and fine-grained criteria through which users assess whether generated images meet their specific requirements. To address this challenge, we propose DyCoRM, a dynamic, criterion-aware reward model that grounds task-relevant criteria and performs criterion-aware preference comparison. To support this setting, we construct DyCoDataset-20K, which provides dynamic criteria together with criterion-level annotations, and further derive DyCoBench-1K, a benchmark for systematically evaluating reward models under dynamic criteria. We further introduce DyCoPick, which applies criterion-aware reward modeling to selecting T2I images. Our contributions establish the first reward modeling framework for dynamic and fine-grained evaluation and practical application in T2I generation.

cs.CV↗

arXiv2026

Generalizable Video Quality Assessment via Weak-to-Strong Learning

Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception, serving as a fundamental tool for quantifying quality degradation across video processing workflows. The dominant VQA paradigm relies on supervised training with human-labeled datasets, which, despite substantial progress, still suffers from poor generalization to unseen video content. In this work, we explore weak-to-strong (W2S) learning as a new paradigm for advancing VQA without reliance on human-labeled datasets. We first provide empirical evidence that a straightforward W2S strategy allows a strong student model to not only match its weak teacher on in-domain benchmarks but also surpass it on out-of-distribution (OOD) benchmarks, revealing a distinct weak-to-strong effect in VQA. Building on this insight, we propose a novel framework that enhances W2S learning from two aspects: (1) integrating homogeneous and heterogeneous supervision signals from diverse VQA teachers -- including off-the-shelf VQA models and synthetic distortion simulators -- via a learn-to-rank formulation, and (2) iterative W2S training, where each strong student is recycled as the teacher in subsequent cycles, progressively focusing on challenging cases. Extensive experiments show that our method achieves state-of-the-art results across both in-domain and OOD benchmarks, with especially strong gains in OOD scenarios. Our findings highlight W2S learning as a principled route to break annotation barriers and achieve scalable generalization in video quality assessment. Our data and code will be available at https://github.com/clh124/W2S-VQA.

cs.CV↗

arXiv2026

Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention

Real-world image super-resolution aims to recover high-quality images from complex and unknown real-world degradations. However, existing generative Real-ISR methods largely inherit the dense latent representations and quadratic-cost global modeling paradigm developed for high-resolution image synthesis, causing computation, memory usage, and inference latency to scale unfavorably with resolution and thus limiting practical deployment. We argue that the key bottleneck lies not in insufficient restoration priors, but in excessive token redundancy and costly token interactions during high-resolution restoration. Motivated by this observation, we revisit Real-ISR from the perspectives of compact latent representation and linear-complexity modeling, and propose SANA-SR, an efficient one-step restoration framework. Specifically, SANA-SR employs a deep compression autoencoder with a 32x compression ratio to drastically reduce latent tokens while preserving restoration-relevant structures and textures. On top of this compact latent space, we introduce a linear-attention DiT with LoRA fine-tuning, enabling efficient high-resolution restoration with linear-complexity token mixing. Extensive experiments on all benchmark datasets demonstrate that SANA-SR achieves highly competitive and often superior quantitative performance against existing methods, while restoring clearer and more realistic textures. Moreover, after pruning, the deployed model runs in 0.019s with 407.95G MACs and 344M parameters, highlighting its strong potential for practical mobile deployment.

cs.CV↗

arXiv2026

Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models

Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One primary difficulty is that a single image can be generated through many different unmasking sequences, which makes calculating importance ratios often intractable. Additionally, existing methods tend to ignore the hierarchical generation process of dMLLMs, where early tokens define the global layout and later tokens focus on local details. By assigning uniform rewards to all tokens, these current methods fail to reflect the actual contribution of each token to the final image. To address these issues, we propose Hierarchical Token GRPO (HT-GRPO), which integrates this hierarchy directly into the policy optimization process. Our approach features a Sketch-Then-Paint training scheme that organizes updates into three distinct stages: global, structure, and refinement. We also use a prompt-conditioned estimator to calculate importance ratios starting from a fully masked state. Furthermore, we introduce a Hierarchical Credit Assignment mechanism that prioritizes key structural tokens to ensure accurate reward propagation. Experiments using two popular dMLLM backbones, MMaDA and Lumina-DiMOO, demonstrate that HT-GRPO achieves substantial gains on the GenEval and DPG benchmarks. Evaluations across six additional metrics confirm significant improvements in image quality, aesthetics, and human preference.

cs.AI↗

arXiv2026

PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow

Adverse weather removal (AWR) in real-world images remains challenging due to heterogeneous and unseen degradations, while distortion-driven training often yields overly smooth results. We propose PVRF, a unified framework that integrates zero-shot soft weather perceptions with velocity-constrained rectified-flow refinement. PVRF introduces an AWR-specific question answering module (AWR-QA) that uses frozen vision--language models (VLMs) to estimate soft probabilities of weather types and low-level attribute scores. These perceptions condition restoration networks via attribute-modulated normalization (AMN) and weather-weighted adapters (WWA), producing an anchor estimate for refinement. We then learn a terminal-consistent residual rectified flow with perception-adaptive source perturbation and a terminal-consistent velocity parameterization to stabilize learning near the terminal regime. Extensive experiments show that PVRF improves both fidelity and perceptual quality over state-of-the-art baselines, with strong cross-dataset generalization on single and combined degradations. Code will be released at https://github.com/dongw22/PVRF.

cs.CV↗

arXiv2026

GeoR-Bench: Evaluating Geoscience Visual Reasoning

Geoscience intelligence is expected to understand, reason about, and predict earth system changes to support human decision-making in critical domains such as disaster response, climate adaptation and environmental protection. Although current research has shown promising progress on specific geoscience tasks, such as remote sensing interpretation, geographic question-answering, existing benchmarks remain largely task-specific which failing to capture the open-ended real world geoscience problems. As a result, it remains unclear how far current AI systems are from achieving genuine geoscience intelligence. To address this gap, we present \textbf{GeoR-Bench}, a \underline{Bench}mark for evaluating \underline{Geo}science visual \underline{R}easoning through reasoning informed visual editing tasks. GeoR-Bench contains 440 curated samples spanning 6 geoscience categories and 24 task types, covering earth observation imagery and structured scientific representations such as maps and diagrams. We evaluate outputs along three dimensions, including reasoning, consistency, and quality. Benchmark results of 21 closed- and open-source multimodal models reveal that geoscience reasoning remains a critical bottleneck. The highest-performing model achieves 42.7\% overall strict accuracy, while the best open-source models only get 10.3\%. Notably, the visual consistency and image quality of the outputs frequently surpass their scientific accuracy. Ultimately, these findings indicate that current models generate superficially plausible results but fail to capture underlying earth science processes.

cs.CV↗