Searcharxiv⌕ Search

arXiv subjects

Yuxiang Cai

Publications and source records attributed to Yuxiang Cai.

At least 19 recordsLinked to original sources
arXiv2026

EliSeg: Verified Target Construction for Report-Grounded Abnormality Segmentation

Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or irrelevant findings, while multiple valid abnormalities may coexist. Existing segmentation methods largely bypass this ambiguity by receiving a target identity or spatial prompt before inference, which acts as a hidden target oracle. We study report-grounded abnormality segmentation, where a model must determine target eligibility, cardinality, and finding-to-mask correspondence directly from an unfiltered report before delineating the corresponding regions. We propose \textbf{EliSeg}, an atcor--verify--revise framework that integrates target construction with mask generation. A grammar-constrained Actor proposes target slots and masks, an independent text-only Verifier reconstructs the eligible finding inventory, and Revision selectively re-executes the shared Actor when their target structures disagree. EliSeg requires no predefined target identity, finding prompt, point, or bounding box. Experiments on MIMIC-CXR-ILS show that EliSeg consistently outperforms direct segmentation methods and extract-then-segment cascades across findings, while effectively suppressing masks for ineligible report mentions. Ablation studies confirm the complementary roles of verification and revision, and evaluation on CheXlocalize demonstrates effective transfer of the EliSeg to an external dataset.Code is available at https://github.com/Maybach-dream/EliSeg.

cs.CV↗
arXiv2026

MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation

Reliable medical image understanding requires models to connect clinical language and visual reasoning with pixel-level grounding. Yet medical vision-language models often lack precise localization, whereas medical segmenters typically rely on explicit target categories or precise spatial prompts. This divide is reinforced by a supervision mismatch: segmentation datasets provide precise masks but little language supervision, whereas medical vision-language data rarely pair language with dense spatial annotations. To address this gap, we present MedPixel, a unified medical pixel-language model built around a shared language--mask interface. To provide scalable supervision, we introduce MedPLG-440K, comprising approximately 440K pixel-language task samples constructed through a clinically motivated synthesis process without external LLM annotation. MedPixel is trained with joint multi-task supervised fine-tuning followed by Pixel-Level Preference Optimization, which uses ground-truth masks as offline verifiers to derive response preferences from mask quality. MedPixel supports a broad spectrum of tasks spanning explicit grounding, implicit reasoning, spatial interaction, grounded explanation, and medical VQA. Across this task spectrum, MedPixel achieves strong performance in both pixel-level prediction and response generation, together with effective zero-shot transfer to external grounding benchmarks and robustness to imperfect spatial prompts. Code and model checkpoints will be released at https://github.com/yhy-whu/Medpixel.

cs.CV↗
arXiv2026

REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering

Recently, retrieval-augmented and memory-augmented methods have emerged as two promising paradigms for long-video question answering. However, existing methods typically rely on rigid, fixed-length temporal chunking (e.g., 10s) and static offline memory banks, which not only fragment coherent continuous events but also fail to adapt during real-time reasoning. Moreover, whether using multi-scale summaries or multimodal knowledge graphs, current approaches prioritize retrieval relevance while overlooking evidence sufficiency, often stopping to answer once only semantically relevant clues are retrieved, even when key temporal, causal, or fine-grained action evidence is still missing. To tackle these challenges, we propose REVEAL, a rubric-guided agent framework. As a foundation, we introduce an adaptive visual-similarity-based preprocessing pipeline that groups visually coherent adjacent frames into natural event units to construct an offline-online video memory---capturing global video context offline while dynamically maintaining question-conditioned memory online. Built upon this structured memory, REVEAL uses an automatically constructed rubric library to explicitly verify whether retrieved evidence satisfies sufficiency criteria, pinpoints missing clues upon verification failure, and directs targeted re-retrieval for complementary information. Without any extra training, REVEAL consistently outperforms both closed-source and open-source state-of-the-art methods across extensive experiments. These results show that explicitly verifying evidence sufficiency, rather than stopping at semantic relevance, retrieves the decisive clues that prior methods miss and yields more reliable long-video reasoning.

cs.CV↗
arXiv2026

SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them

Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that reasoning. However, a fundamental capability mismatch remains: general VLMs can reason about the overall task but often miss the visual details that determine success, while specialist vision models can capture those details but cannot translate them into task-level decisions. In this work, we propose SpatialCLI, a framework that teaches VLMs to reason with spatial tools and progressively internalize the specialist perceptual capabilities they provide. SpatialCLI proceeds in three stages: (1) Call exposes specialist vision models as spatial tools to augment the VLM's perception; (2) Learn uses Cold-Start SFT and agentic RL to improve tool use; and (3) Internalize verbalizes successful tool-use trajectories to internalize specialist perceptual capabilities. We further introduce SpatialCLI-Bench, a 516-example benchmark for compositional perception across localization, segmentation, depth, and pose. On MindCube, SpatialCLI raises Qwen3-VL-8B-Instruct from 29.3% to 84.6% with tools, surpassing GPT-5.6 Sol with tools (72.1%), while retaining 73.8% without tools after internalization.

cs.AI↗
arXiv2026

Continual Video-MLLM Adaptation over Evolving Domains

Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains. DAER maintains domain-isolated lightweight experts while keeping the pretrained Video-MLLM backbone frozen, thereby decoupling domain-specific adaptation from the general multimodal knowledge of the pretrained model. To enable fine-grained specialization, we introduce an intra-domain distribution-aware routing mechanism that matches each input to expert-level prototype reservoirs using MMD. To address the absence of task identities at inference time, we further propose an inter-domain routing mechanism that performs prototype matching in a discriminative subspace for robust domain identification. In addition, we introduce adaptive domain merging to improve parameter scalability and adopt a two-stage optimization strategy to stabilize expert specialization during continual learning. We evaluate DAER by curating a domain-incremental benchmark built from ten VidQA datasets covering diverse visual environments and reasoning demands. Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.

cs.CV↗
arXiv2026

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA games, simulation engines, and internet videos to learn controllable world dynamics. WorldExplorer performs agent-driven collection guided by training feedback, while a unified pipeline applies 14 deterministic quality checks, VLM-based assessment, and synchronized action and text annotation. We progressively distill a bidirectional action-conditioned teacher into a causal student through teacher forcing and ODE distillation, and introduce LongForcing to align long student self-rollouts with an extended-horizon teacher, mitigating accumulated distribution shift and autoregressive drift. Raw keyboard actions provide a unified control interface for scene roaming and third-person character interaction, while reference-character memory provides persistent appearance cues for identity consistency during third-person rollouts. For deployment, we co-design a streaming inference stack with a lightweight VAE decoder, efficient attention, memory-aware scheduling, and low-bit DiT inference. Across optimized low-bit configurations, ABot-World-0 streams 720P video at up to 16 FPS on a single NVIDIA RTX 5090 desktop GPU, with 1.2s action-to-first-frame latency and approximately 19GiB peak VRAM. Experiments on WorldRoamBench and extended interactive rollouts demonstrate competitive controllability and coherent long-horizon world evolution.

cs.CV↗
arXiv2026

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual attention scores. However, we show that attention is often dominated by a model-induced prior: even without textual instruction, MLLMs tend to focus on certain task-agnostic regions. Consequently, the attention scores of instruction-conditioned tokens are suppressed, increasing the risk that these tokens are discarded during pruning. To address this issue, we propose Prior-Corrected Token Reduction (PriorTR), a training-free token reduction method that explicitly separates task-conditioned attention from the model-induced prior. PriorTR estimates the attention map of the prior, and contrasts it with the task-conditioned attention distribution to measure the additional usable information contributed by each visual token. Importantly, PriorTR computes both the model-induced prior and the task-conditioned posterior within a single forward pass by introducing a null token that serves as an instruction-agnostic probe in the attention block. This design avoids duplicated propagation. Extensive experiments across multiple multimodal benchmarks and MLLMs demonstrate that PriorTR consistently improves the trade-off between accuracy and efficiency over strong training-free baselines, particularly under aggressive token budgets.

cs.CV↗
arXiv2026

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models

Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performance. Existing token pruning methods typically rely on single-layer signals, such as attention scores or token similarities, which overlook the cross-layer transformation of visual representations and may exhibit positional bias in multimodal token sequences. To address this limitation, we propose a training-free token pruning framework based on Cross-Layer Spectral Evolution (CLSE). Instead of measuring token importance from single-layer feature magnitudes, CLSE quantifies how token representations evolve across Transformer layers in the frequency domain. This evolution reflects the transition from high-frequency structural details to low-frequency semantic abstractions. We observe that tokens with stronger spectral redistribution across layers are more likely to be semantically active and should therefore be preserved. By modeling cross-layer token dynamics, CLSE provides a stable importance criterion that mitigates positional bias. Extensive experiments on both image and video benchmarks demonstrate that CLSE achieves a superior trade-off between efficiency and accuracy under aggressive token reduction. Across multiple MLLMs, CLSE reduces FLOPs, KV cache memory, and latency while maintaining competitive or improved performance.

cs.CV↗
arXiv2026

GLIDE: Graph-guided Leap Inference for Diffusion Estimation of Spatio-Temporal Point Processes

Spatio-temporal point processes (STPPs) provide a principled framework for modeling asynchronous events in continuous time and space. Recent diffusion-based approaches offer a flexible alternative to deterministic prediction by modeling complex conditional distributions, but their application to STPPs remains challenging: reverse sampling from pure noise is costly, and weak structural constraints in sparse spatial domains can lead to poorly localized probability mass. We propose \textbf{GLIDE} (Graph-guided Leap Inference for Diffusion Estimation), a conditional diffusion framework for next-event modeling in STPPs. GLIDE organizes historical events into a multi-scale historical graph and encodes temporal evolution and spatial topology through a dual-stream architecture, yielding a structured conditioning context for a dual-branch diffusion denoiser. It further introduces a prior-guided leap inference mechanism, in which a lightweight mean predictor provides a deterministic anchor and the reverse process starts from an intermediate diffusion step instead of from pure Gaussian noise. Experiments on multiple real-world datasets show that GLIDE improves both distribution fitting and next-event prediction, with the largest gains appearing on the spatial side. The results also indicate that prior-guided leap inference substantially reduces reverse-sampling cost while preserving the stochastic generation capability of diffusion models.

cs.LG↗
arXiv2026

FAiT: Frequency-Aware Inverted Transformer for Multivariate Time Series Forecasting

While Transformer-based architectures have established themselves as a dominant paradigm in Multivariate Time Series Forecasting (MTSF), their core self-attention mechanism inherently functions as a low-pass filter, systematically smoothing out high-frequency signals vital for sharp local changes. Recent advancements have increasingly incorporated frequency-domain operations to address this bias, however, most existing designs rely on fixed spectral bases and apply sequence-wise (uniform) modulation, implicitly assuming a time-invariant frequency response. This overlooks a key property of real-world series that their spectral characteristics often evolve over time, making uniform modulation insufficient for capturing fine-grained temporal dynamics. To tackle these limitations, we propose FAiT, a Frequency-Aware inverted Transformer. Specifically, FAiT rectifies the spectral bias internally through Inverted Attention, which interprets the attention map as a learnable low-pass operator and constructs a dedicated complementary high-pass branch by inverting the attention matrix to recover attenuated transient signals. Furthermore, FAiT introduces Dynamic Temporal-Frequency Modulation (DTFM), which synthesizes instance-conditioned weights to adaptively re-calibrate the energy of spectral sub-bands, enabling fine-grained control over evolving multi-scale patterns. Extensive experiments on widely used benchmarks demonstrate that FAiT consistently outperforms state-of-the-art Transformer-based and frequency-enhanced baselines, while maintaining computational efficiency.

cs.LG↗
arXiv2026

Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding

MLLMs frequently hallucinate objects inconsistent with visual inputs. This issue is typically attributed to the over-reliance on language priors, which can override the visual context. Recent training-free decoding strategies address this by penalizing language priors. However, these methods overlook the dual nature of language priors, where they can be both helpful and harmful depending on the alignment with visual evidence. In particular, blindly suppressing language priors often disrupts the model's semantic manifold, leading to performance degradation, a phenomenon we term Manifold Departure. To address this, we propose Manifold-Guided Adaptive Projection (MGAP), a geometry-aware, training-free decoding method that mitigates hallucinations while preserving representation structure. MGAP first constructs a language-prior subspace from blind hidden states via SVD. During decoding, MGAP projects each multimodal hidden state onto this subspace and applies a consistency-aware gate to adaptively attenuate only the projected prior component, yielding a subspace-selective update that largely preserves the orthogonal semantic components. Extensive experiments on POPE and CHAIR show that MGAP outperforms prior decoding baselines, achieving stronger hallucination suppression without sacrificing coherence.

cs.LG↗
arXiv2026

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs

Latent reasoning enables reasoning over continuous hidden states rather than explicit tokens, avoiding the language bottleneck and inference overhead of chain-of-thought for medical VQA. However, existing methods suffer from modality collapse, insufficient visual supervision, and train-inference mismatch. Moreover, their opaque latent states offer no interpretability, which is critical in clinical applications. We propose VITAL, a latent-space reasoning framework for medical MLLMs with visual-semantic dual supervision: an auxiliary text decoder reconstructs reasoning chains from latent states, while a visual projector regresses ROI features from a frozen, independent medical vision encoder. Both modules are discarded at inference with zero overhead, yet can be re-attached post-hoc for dual interpretability, providing textual and visual explanations of the reasoning process without sacrificing efficiency. We construct a 61K dataset spanning 9 imaging modalities, exceeding prior medical visual latent reasoning datasets by an order of magnitude. Experiments on 7 benchmarks show that VITAL consistently and substantially outperforms the backbone, all latent reasoning baselines, and medical MLLMs trained on far larger data, achieving state-of-the-art results competitive with trillion-parameter proprietary models.

cs.CV↗
arXiv2026

Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning

Referring expression understanding in remote sensing poses unique challenges, as it requires reasoning over complex object-context relationships. While supervised fine-tuning (SFT) on multimodal large language models achieves strong performance with massive labeled datasets, they struggle in data-scarce scenarios, leading to poor generalization. To address this limitation, we propose Geo-R1, a reasoning-centric reinforcement fine-tuning (RFT) paradigm for few-shot geospatial referring. Geo-R1 enforces the model to first generate explicit, interpretable reasoning chains that decompose referring expressions, and then leverage these rationales to localize target objects. This "reason first, then act" process enables the model to make more effective use of limited annotations, enhances generalization, and provides interpretability. We validate Geo-R1 on three carefully designed few-shot geospatial referring benchmarks, where our model consistently and substantially outperforms SFT baselines. It also demonstrates strong cross-dataset generalization, highlighting its robustness. Code and data will be released at: https://github.com/Geo-R1/geo-r1.

cs.CV↗
arXiv2026

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation

Recent research on medical MLLMs has gradually shifted its focus from image-level understanding to fine-grained, pixel-level comprehension. Although segmentation serves as the foundation for pixel-level understanding, existing approaches face two major challenges. First, they introduce implicit segmentation tokens and require simultaneous fine-tuning of both the MLLM and external pixel decoders, which increases the risk of catastrophic forgetting and limits generalization to out-of-domain scenarios. Second, most methods rely on single-pass reasoning and lack the capability to iteratively refine segmentation results, leading to suboptimal performance. To overcome these limitations, we propose a novel agentic MLLM, named IBISAgent, that reformulates segmentation as a vision-centric, multi-step decision-making process. IBISAgent enables MLLMs to generate interleaved reasoning and text-based click actions, invoke segmentation tools, and produce high-quality masks without architectural modifications. By iteratively performing multi-step visual reasoning on masked image features, IBISAgent naturally supports mask refinement and promotes the development of pixel-level visual reasoning capabilities. We further design a two-stage training framework consisting of cold-start supervised fine-tuning and agentic reinforcement learning with tailored, fine-grained rewards, enhancing the model's robustness in complex medical referring and reasoning segmentation tasks. Extensive experiments demonstrate that IBISAgent consistently outperforms both closed-source and open-source SOTA methods.

cs.CV↗
arXiv2026

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tuning, current methods are susceptible to overfitting and often underperform, sometimes generating unnatural outputs. We hypothesize that this is because effective steering requires the faithful identification of internal model mechanisms, not the enforcement of external preferences. To this end, we build on the principles of distributed alignment search (DAS), the standard for causal variable localization, to propose a new steering method: Concept DAS (CDAS). While we adopt the core mechanism of DAS, distributed interchange intervention (DII), we introduce a novel distribution matching objective tailored for the steering task by aligning intervened output distributions with counterfactual distributions. CDAS differs from prior work in two main ways: first, it learns interventions via weak-supervised distribution matching rather than probability maximization; second, it uses DIIs that naturally enable bi-directional steering and allow steering factors to be derived from data, reducing the effort required for hyperparameter tuning and resulting in more faithful and stable control. On AxBench, a large-scale model steering benchmark, we show that CDAS does not always outperform preference-optimization methods but may benefit more from increased model scale. In two safety-related case studies, overriding refusal behaviors of safety-aligned models and neutralizing a chain-of-thought backdoor, CDAS achieves systematic steering while maintaining general model utility. These results indicate that CDAS is complementary to preference-optimization approaches and conditionally constitutes a robust approach to intervention-based model steering. Our code is available at https://github.com/colored-dye/concept_das.

cs.LG↗
arXiv2026

Learning Multi-Modal Prototypes for Cross-Domain Few-Shot Object Detection

Cross-Domain Few-Shot Object Detection (CD-FSOD) aims to detect novel classes in unseen target domains given only a few labeled examples. While open-vocabulary detectors built on vision-language models (VLMs) transfer well, they depend almost entirely on text prompts, which encode domain-invariant semantics but miss domain-specific visual information needed for precise localization under few-shot supervision. We propose a dual-branch detector that Learns Multi-modal Prototypes, dubbed LMP, by coupling textual guidance with visual exemplars drawn from the target domain. A Visual Prototype Construction module aggregates class-level prototypes from support RoIs and dynamically generates hard-negative prototypes in query images via jittered boxes, capturing distractors and visually similar backgrounds. In the visual-guided branch, we inject these prototypes into the detection pipeline with components mirrored from the text branch as the starting point for training, while a parallel text-guided branch preserves open-vocabulary semantics. The branches are trained jointly and ensembled at inference by combining semantic abstraction with domain-adaptive details. On six cross-domain benchmark datasets and standard 1/5/10-shot settings, our method achieves state-of-the-art or highly competitive mAP.

cs.CV↗
arXiv2026

Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation

Temporal Knowledge Graph (TKG) reasoning seeks to predict future missing facts from historical evidence. While diffusion models (DM) have recently gained attention for their ability to capture complex predictive distributions, two gaps remain: (i) the generative path is conditioned only on positive evidence, overlooking informative negative context, and (ii) training objectives are dominated by cross-entropy ranking, which improves candidate ordering but provides little supervision over the calibration of the denoised embedding. To bridge this gap, we introduce Negative-Aware Diffusion model for TKG Extrapolation (NADEx). Specifically, NADEx encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings. NADEx perturbs the query object in the forward process and reconstructs it in reverse with a Transformer denoiser conditioned on the temporal-relational context. We further derive a cosine-alignment regularizer derived from batch-wise negative prototypes, which tightens the decision boundary against implausible candidates. Comprehensive experiments on four public TKG benchmarks demonstrate that NADEx delivers state-of-the-art performance.

cs.AI↗
arXiv2025

Fine-Grained Zero-Shot Learning with Attribute-Centric Representations

Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships from seen classes to unseen classes. The core challenge is attribute entanglement, where conventional models collapse distinct attributes like color, shape, and texture into a single visual embedding. This causes interference that masks these critical distinctions. The post-hoc solutions of previous work are insufficient, as they operate on representations that are already mixed. We propose a zero-shot learning framework that learns AttributeCentric Representations (ACR) to tackle this problem by imposing attribute disentanglement during representation learning. ACR is achieved with two mixture-of-experts components, including Mixture of Patch Experts (MoPE) and Mixture of Attribute Experts (MoAE). First, MoPE is inserted into the transformer using a dual-level routing mechanism to conditionally dispatch image patches to specialized experts. This ensures coherent attribute families are processed by dedicated experts. Finally, the MoAE head projects these expert-refined features into sparse, partaware attribute maps for robust zero-shot classification. On zero-shot learning benchmark datasets CUB, AwA2, and SUN, our ACR achieves consistent state-of-the-art results.

cs.CV↗