arXiv subjects

Lang Lin

Publications and source records attributed to Lang Lin.

6 recordsLinked to original sources

arXiv2026

Why Does Grounding Hurt Medical VQA? Benchmarking, Diagnosis, and Fine-Tuning of Vision-Language Models

Vision-language models (VLMs) are increasingly applied to medical visual question answering (Med-VQA), yet whether they can \emph{localize} the evidence behind their answers---a prerequisite for clinical auditability---is poorly characterized. We separately evaluate VQA reasoning and visual grounding for four recent frontier VLMs (GPT-5.1, GPT-5.5, Gemini-2.5-Pro, Gemini-3-Flash), two domain-specific medical VLMs (Lingshu, MedGemma), and a dedicated open-vocabulary detector (Grounding DINO) on VQA-RAD and SLAKE. Two findings challenge the intuition that ``add grounding to improve VQA.'' First, \textbf{no model localizes medical targets well}: every off-the-shelf system---frontier, medical-specialized, or dedicated detector---scores mean IoU 0.05--0.24 on our SLAKE grounding split, at or barely above a trivial center-box baseline (0.10), with Acc@0.5 below 20\%. Second, and counter to the common ``localize-then-answer'' paradigm, \textbf{cropping to a bounding box degrades VQA even when the box is a perfect oracle}: on the matched subset where oracle ground-truth boxes are applied, GT-grounding \emph{lowers} closed-ended accuracy for every model (by 0.9--18.0 points versus using the full image)---consistent with the crop discarding global context the model relies on. Because the oracle box removes localization error by construction, the problem is not that perception is a recoverable bottleneck, but that grounding-by-cropping is itself the wrong interface. Finally, we show constructively that the two channels need not conflict: supervised fine-tuning of Qwen-2.5-VL-7B on answers \emph{alone} silently destroys box-evidence emission (0/418 parseable boxes), whereas mixing in a small amount of grounding supervision restores localization to 0.36 IoU---above every zero-shot model---while preserving answer accuracy.

cs.AI↗

arXiv2026

Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode

Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation efficiency. Beyond the utility benefits, we argue that D-LLMs exhibit a previously underexplored safety blessing: their diffusion-style generation confers intrinsic robustness against jailbreak attacks originally designed for AR-LLMs. In this work, we provide an initial analysis of the underlying mechanism, showing that the diffusion trajectory induces a stepwise reduction effect that progressively suppresses unsafe generations. This robustness, however, is not absolute. Following this analysis, we highlight a simple yet effective failure mode, context nesting, in which harmful requests are embedded within structured benign contexts. Empirically, we show that this simple black-box strategy bypasses D-LLMs' safety blessing, achieving state-of-the-art attack success rates across models and benchmarks. Notably, it enables the first successful jailbreak of Gemini Diffusion to our knowledge, exposing a critical vulnerability in proprietary D-LLMs. Together, our results characterize both the origins and the limits of D-LLMs' safety blessing, constituting an early-stage red-teaming of D-LLMs.

cs.LG↗

arXiv2025

InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision

Large-scale video-text pretraining achieves strong performance but depends on noisy, synthetic captions with limited semantic coverage, often overlooking implicit world knowledge such as object motion, 3D geometry, and physical cues. In contrast, masked video modeling (MVM) directly exploits spatiotemporal structures but trails text-supervised methods on general tasks. We find this gap arises from overlooked architectural issues: pixel-level reconstruction struggles with convergence and its low-level requirement often conflicts with semantics, while latent prediction often encourages shortcut learning. To address these, we disentangle the traditional encoder-decoder design into an Encoder-Predictor-Decoder (EPD) framework, where the predictor acts as a latent world model, and propose InternVideo-Next, a two-stage pretraining scheme that builds a semantically consistent yet detail-preserving latent space for this world model. First, conventional linear decoder in pixel MVM enforces the predictor output latent to be linearly projected to, thus separable in pixel space, causing the conflict with semantic abstraction. Our Stage 1 proposes a conditional diffusion decoder and injects reliable image-level semantic priors to enhance semantics and convergence, thus bridging pixel-level fidelity with high-level semantic abstraction. Stage 2 further learns world knowledge by predicting frozen Stage 1 targets within this space, mitigating shortcut learning. Trained on public, unlabeled videos, InternVideo-Next achieves state-of-the-art results across benchmarks and provides a scalable path toward general video representation learning.

cs.CV↗

arXiv2025

GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation

This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly struggle with the dilemma between "Ref" and "VOS": they either specialize in understanding a few key frames (global reasoning) or tracking objects on continuous frames (local reasoning), and rely on external VOS or frame selectors to mitigate the other end of the challenge. However, our framework GLUS shows that global and local consistency can be unified into a single video segmentation MLLM: a set of sparse "context frames" provides global information, while a stream of continuous "query frames" conducts local object tracking. This is further supported by jointly training the MLLM with a pre-trained VOS memory bank to simultaneously digest short-range and long-range temporal information. To improve the information efficiency within the limited context window of MLLMs, we introduce object contrastive learning to distinguish hard false-positive objects and a self-refined framework to identify crucial frames and perform propagation. By collectively integrating these insights, our GLUS delivers a simple yet effective baseline, achieving new state-of-the-art for MLLMs on the MeViS and Ref-Youtube-VOS benchmark. Our project page is at https://glus-video.github.io/.

cs.CV↗

arXiv2024

Improving Location-based Thermal Emission Side-Channel Analysis Using Iterative Transfer Learning

This paper proposes the use of iterative transfer learning applied to deep learning models for side-channel attacks. Currently, most of the side-channel attack methods train a model for each individual byte, without considering the correlation between bytes. However, since the models' parameters for attacking different bytes may be similar, we can leverage transfer learning, meaning that we first train the model for one of the key bytes, then use the trained model as a pretrained model for the remaining bytes. This technique can be applied iteratively, a process known as iterative transfer learning. Experimental results show that when using thermal or power consumption map images as input, and multilayer perceptron or convolutional neural network as the model, our method improves average performance, especially when the amount of data is insufficient.

cs.LG↗

arXiv2023

A Plug-and-Play Defensive Perturbation for Copyright Protection of DNN-based Applications

Wide deployment of deep neural networks (DNNs) based applications (e.g., style transfer, cartoonish), stimulating the requirement of copyright protection of such application's production. Although some traditional visible copyright techniques are available, they would introduce undesired traces and result in a poor user experience. In this paper, we propose a novel plug-and-play invisible copyright protection method based on defensive perturbation for DNN-based applications (i.e., style transfer). Rather than apply the perturbation to attack the DNNs model, we explore the potential utilization of perturbation in copyright protection. Specifically, we project the copyright information to the defensive perturbation with the designed copyright encoder, which is added to the image to be protected. Then, we extract the copyright information from the encoded copyrighted image with the devised copyright decoder. Furthermore, we use a robustness module to strengthen the decoding capability of the decoder toward images with various distortions (e.g., JPEG compression), which may be occurred when the user posts the image on social media. To ensure the image quality of encoded images and decoded copyright images, a loss function was elaborately devised. Objective and subjective experiment results demonstrate the effectiveness of the proposed method. We have also conducted physical world tests on social media (i.e., Wechat and Twitter) by posting encoded copyright images. The results show that the copyright information in the encoded image saved from social media can still be correctly extracted.

cs.CV↗