Search arXiv⌕ Search

arXiv subjects

Ngan Le

Publications and source records attributed to Ngan Le.

At least 37 records · Page 2Linked to original sources
arXiv2026

PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering

Generative diffusion models are increasingly used for medical imaging data augmentation, but text prompting cannot produce causal training data. Re-prompting rerolls the entire generation trajectory, altering anatomy, texture, and background. Inversion-based editing methods introduce reconstruction error that causes structural drift. We propose PolypSteer, a training-free activation-steering framework for endoscopic synthesis. PolypSteer identifies a pathology vector for each contrastive prompt pair in the cross-attention layers of a diffusion transformer. At inference time, it steers image activations along this vector, generating counterfactual pairs from scratch where the only difference is the steered concept. All other structure is preserved by construction. We evaluate PolypSteer across three experiments on Kvasir v3 and HyperKvasir. On counterfactual generation across three clinical concept pairs, PolypSteer achieves flip rates of 0.800, 0.925, and 0.950, outperforming the best inversion-based baseline in both concept flip rate and structural preservation. On dye disentanglement, PolypSteer achieves 75% dye removal against 20% (PnP) and 10% (h-Edit). On downstream polyp detection, augmenting with PolypSteer counterfactual pairs achieves ViT AUC of 0.9755 versus 0.9083 for quantity-matched re-prompting, confirming that counterfactual structure drives the gain. Code is at link https://github.com/UARK-AICV/PolypSteer

cs.CV↗
arXiv2026

MVDGC: Joint 3D and 2D Multi-view Pedestrian Detection via Dual Geometric Constraints

The core challenge in multi-view pedestrian detection (MVPD) lies in effective aggregation of visual features from different viewpoints for robust occlusion reasoning. Recent approaches have addressed this by first projecting image-view features onto a Bird's Eye View (BEV) map, where ground localization is then performed. Despite impressive performance, the perspective transformation induces severe distortion, causing spatial structure break and degrading the quality of object feature extraction. The blurred and ambiguous features hinder accurate BEV point localization, especially in densely populated regions. Moreover, the strong mutual relationship between the BEV ground point and image bounding boxes is not capitalized on. Although multi-view consistency of 2D detections can serve as a powerful constraint in BEV space, these detections are commonly treated as auxiliary signals rather than being jointly optimized with the primary task.In this work, we propose \textbf{MVDGC}, a unified framework that \emph{jointly estimates pedestrian locations on the BEV plane and 2D bounding boxes in image views}. MVDGC employs a \emph{sparse set of 3D cylindrical queries} that embraces geometric context across both BEV and image views, enforcing dual spatial constraints for precise localization. Specifically, the geometric constraints is established by modeling each pedestrian as a vertical cylinder whose center lies on the BEV plane and whose projection casts a rectangular box in the image views. These queries function as shape anchors that directly extract 2D features from the intact image-view features using camera projection, eliminating projection-induced distortions. The 3D cylindrical query enables the unification of BEV and ImV localization into a single task: 3D cylinder position and shape refinement. Code is available at: https://github.com/UARK-AICV/MVDGC

cs.CV↗
arXiv2026

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models

Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining. However, their direct application to the Segment Anything Model (SAM) family is nontrivial: SAM's image encoder mixes windowed and global attention, and its mask decoder relies on dense, prompt-conditioned features for precise boundary prediction. We systematically evaluate representative token-merging methods on SAM and Medical SAM in a strict off-the-shelf setting, and find that existing destination-selection heuristics can erode boundaries and leak prompt information as merge rates increase. We propose \textbf{StructSAM}, a resolution-preserving merge-unmerge framework tailored to SAM. StructSAM computes a lightweight token-energy score from first-order feature gradients, uses grid-based flatness screening to protect boundary and prompt regions, and merges tokens within flat areas toward low-energy destinations with explicit token recovery. We further provide a spectral graph coarsening view showing that score-guided merging yields bounded Laplacian spectral distortion compared to random or window-restricted baselines. Across eight natural and medical benchmarks, StructSAM reduces encoder FLOPs by 25-30\% (up to 40\%+ with prompt-aware merging) with minor drops in mIoU/Dice, consistently outperforming ToMe, PiToMe, ToMeSD, VidToMe, and ALGM at the same compute.

cs.CV↗
arXiv2026

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think

Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference. In this work, we reveal a highly non-trivial architectural characteristic of these continuous control foundation policies (e.g., pi_0, GR00T-N1.5): despite being trained on diverse physical trajectories, they exhibit severe layer-wise representational redundancy. To exploit this, we introduce a structural compression pipeline that is entirely training-free, bypassing the need of existing methods to load full-scale models to learn optimized token reductions or dynamic layer selectors. Instead, using only a single forward pass via Centered Kernel Alignment to identify redundant layer features, we remove twin layers to permanently compress the model depth by up to 50% across both the VLM backbone and the continuous control policy head. Downstream fine-tuning of this streamlined architecture yields a dual acceleration benefit: a 40-50% reduction in training time and up to 30% faster real-time inference, while matching or exceeding full-scale base model performance. We comprehensively validate our method across three simulation benchmarks (LIBERO, RoboCasa, SimplerEnv) and 10 diverse real-world manipulation tasks across 4 unique robotic embodiments. These results prove that advanced VLAs require significantly fewer layers than previously assumed, offering a highly compute-efficient paradigm for scalable robot learning.

cs.RO↗
arXiv2026

ARGUSTRACK: A Multi-View Annotation System for Multi-Object Tracking

Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monitoring. While recent advances have yielded sophisticated tracking algorithms, the availability of annotated multi-view data remains a significant bottleneck. Existing annotation tools predominantly support single-camera workflows or rely on LiDAR sensors, making cross-view labeling tedious and impractical for camera-only setups. We present ARGUS-TRACK, a multi-camera annotation system that addresses these limitations by enabling annotators to work directly on a bird's-eye-view (BEV) plane. Given calibrated camera parameters, a single ground-plane annotation is automatically projected into 2D bounding boxes across all relevant views, inherently ensuring identity consistency without manual cross-view alignment. To further accelerate the labeling process, ARGUSTRACK incorporates two complementary mechanisms: a Temporal Aware module that propagates annotations from preceding frames to initialize new ones, requiring only minor positional adjustments; and a Multi-camera Semi-annotation module that leverages off-the-shelf 2D detectors combined with foot-point estimation to automatically generate candidate BEV positions for annotator verification. We evaluate ARGUSTRACK through a pilot study on multi-camera broiler tracking and demonstrate that it substantially reduces annotation time compared to conventional single-camera labeling workflows.

cs.CV↗
arXiv2026

CodeGraphVLP: Code-as-Planner Meets Semantic-Graph State for Non-Markovian Vision-Language-Action Models

Vision-Language-Action (VLA) models promise generalist robot manipulation, but are typically trained and deployed as short-horizon policies that assume the latest observation is sufficient for action reasoning. This assumption breaks in non-Markovian long-horizon tasks, where task-relevant evidence can be occluded or appear only earlier in the trajectory, and where clutter and distractors make fine-grained visual grounding brittle. We present CodeGraphVLP, a hierarchical framework that enables reliable long-horizon manipulation by combining a persistent semantic-graph state with an executable code-based planner and progress-guided visual-language prompting. The semantic-graph maintains task-relevant entities and relations under partial observability. The synthesized planner executes over this semantic-graph to perform efficient progress checks and outputs a subtask instruction together with subtask-relevant objects. We use these outputs to construct clutter-suppressed observations that focus the VLA executor on critical evidence. On real-world non-Markovian tasks, CodeGraphVLP improves task completion over strong VLA baselines and history-enabled variants while substantially lowering planning latency compared to VLM-in-the-loop planning. We also conduct extensive ablation studies to confirm the contributions of each component.

cs.RO↗
arXiv2026

3D B-fieLds in the InterStellar medium and Star-forming regions (3D-BLISS): I. Using Starlight Polarization in the Massive IRDC Filament G11.11-0.12

Measuring three-dimensional magnetic fields (3D B-fields) is essential to understand the formation and evolution of the interstellar medium and multi-scale star formation; however, the accurate measurement of 3D B-fields is still challenging. The dust polarization angles by magnetically aligned grains provide the projected B-fields onto the plane-of-sky, while the dust polarization degree provides the B-field's inclination angle with respect to the line-of-sight. Our previous theoretical studies proposed a new method of probing 3D B-fields using dust polarization combined with the Radiative Torque (RAT) alignment theory and demonstrated the accurate inference of B-field inclination angles using synthetic polarization data. In this paper, we report the first application of the new technique to study 3D B-fields and dust properties in the G11.11-0.12 filament (hereafter G11) from starlight polarization observations taken by ISRF/SIRPOL at $2.19\,\rmμm$. Using both observed starlight polarization and optical dust extinction curves from the Gaia mission, we constrained the maximum grain size of $0.25\,\rmμm$ and the grain elongation with an axial ratio of $s\gtrsim 1.4$ in the outer regions of G11. We calculated the alignment properties in G11 by using the \textsc{DustPOL\_py} code. The B-field's inclination angles in G11 are then inferred from the observed starlight polarization efficiency when the grain alignment is included, with a mean angle of $\sim 48$ degrees. From these inferred inclination angles, we found evidence of the local 3D arc-shaped B-field structure toward the sightline. These findings are important for understanding 3D B-field's roles in the formation and evolution of massive filamentary clouds.

astro-ph.GA↗
arXiv2026

DuFal: Dual-Frequency-Aware Learning for High-Fidelity Extremely Sparse-view CBCT Reconstruction

Sparse-view Cone-Beam Computed Tomography reconstruction from limited X-ray projections remains a challenging problem in medical imaging due to the inherent undersampling of fine-grained anatomical details, which correspond to high-frequency components. Conventional CNN-based methods often struggle to recover these fine structures, as they are typically biased toward learning low-frequency information. To address this challenge, this paper presents DuFal (Dual-Frequency-Aware Learning), a novel framework that integrates frequency-domain and spatial-domain processing via a dual-path architecture. The core innovation lies in our High-Local Factorized Fourier Neural Operator, which comprises two complementary branches: a Global High-Frequency Enhanced Fourier Neural Operator that captures global frequency patterns and a Local High-Frequency Enhanced Fourier Neural Operator that processes spatially partitioned patches to preserve spatial locality that might be lost in global frequency analysis. To improve efficiency, we design a Spectral-Channel Factorization scheme that reduces the Fourier Neural Operator parameter count. We also design a Cross-Attention Frequency Fusion module to integrate spatial and frequency features effectively. The fused features are then decoded through a Feature Decoder to produce projection representations, which are subsequently processed through an Intensity Field Decoding pipeline to reconstruct a final Computed Tomography volume. Experimental results on the LUNA16 and ToothFairy datasets demonstrate that DuFal significantly outperforms existing state-of-the-art methods in preserving high-frequency anatomical features, particularly under extremely sparse-view settings.

cs.CV↗
arXiv2026

Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding

Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action prediction. Yet most VLAs entangle perception and control in a monolithic pipeline optimized purely for action, which can erode language-conditioned grounding. In our real-world tabletop tests, policies over-grasp when the target is absent, are distracted by clutter, and overfit to background appearance. To address these issues, we propose OBEYED-VLA (OBject-centric and gEometrY groundED VLA), a framework that explicitly disentangles perceptual grounding from action reasoning. Instead of operating directly on raw RGB, OBEYED-VLA augments VLAs with a perception module that grounds multi-view inputs into task-conditioned, object-centric, and geometry-aware observations. This module includes a VLM-based object-centric grounding stage that selects task-relevant object regions across camera views, along with a complementary geometric grounding stage that emphasizes the 3D structure of these objects over their appearance. The resulting grounded views are then fed to a pretrained VLA policy, which we fine-tune exclusively on single-object demonstrations collected without environmental clutter or non-target objects. On a real-world UR10e tabletop setup, OBEYED-VLA substantially improves robustness over strong VLA baselines across four challenging regimes and multiple difficulty levels: distractor objects, absent-target rejection, background appearance changes, and cluttered manipulation of unseen objects. Ablation studies confirm that both semantic grounding and geometry-aware grounding are critical to these gains. Overall, the results indicate that making perception an explicit, object-centric component is an effective way to strengthen and generalize VLA-based robotic manipulation.

cs.RO↗
arXiv2026

SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection

Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily prioritize overall performance while overlooking the severe long-tail imbalance inherent in real-world datasets. In practice, many rare but safety-critical categories such as children, strollers, or emergency vehicles are heavily underrepresented, leading to biased learning and degraded performance. This challenge is further exacerbated by pronounced inter-class ambiguity (e.g., visually similar subclasses) and substantial intra-class diversity (e.g., objects varying widely in appearance, scale, pose, or context), which together hinder reliable long-tail recognition. In this work, we introduce SemLT3D, a Semantic-Guided Expert Distillation framework designed to enrich the representation space for underrepresented classes through semantic priors. SemLT3D consists of: (1) a language-guided mixture-of-experts module that routes 3D queries to specialized experts according to their semantic affinity, enabling the model to better disentangle confusing classes and specialize on tail distributions; and (2) a semantic projection distillation pipeline that aligns 3D queries with CLIP-informed 2D semantics, producing more coherent and discriminative features across diverse visual manifestations. Although motivated by long-tail imbalance, the semantically structured learning in SemLT3D also improves robustness under broader appearance variations and challenging corner cases, offering a principled step toward more reliable camera-only 3D perception.

cs.CV↗
arXiv2026

GazeQwen: Lightweight Gaze-Conditioned LLM Modulation for Streaming Video Understanding

Current multimodal large language models (MLLMs) cannot effectively utilize eye-gaze information for video understanding, even when gaze cues are supplied via visual overlays or text descriptions. We introduce GazeQwen, a parameter efficient approach that equips an open-source MLLM with gaze awareness through hidden-state modulation. At its core is a compact gaze resampler (~1-5 M trainable parameters) that encodes V-JEPA 2.1 video features together with fixation-derived positional encodings and produces additive residuals injected into selected LLM decoder layers via forward hooks. An optional second training stage adds low-rank adapters (LoRA) to the LLM for tighter integration. Evaluated on all 10 tasks of the StreamGaze benchmark, GazeQwen reaches 63.9% accuracy, a +16.1 point gain over the same Qwen2.5-VL-7B backbone with gaze as visual prompts and +10.5 points over GPT-4o, the highest score among all open-source and proprietary models tested. These results suggest that learning where to inject gaze within an LLM is more effective than scaling model size or engineering better prompts. All code and checkpoints are available at https://github.com/phamtrongthang123/gazeqwen .

cs.CV↗
arXiv2026

SIGMA: A Physics-Based Benchmark for Gas Chimney Understanding in Seismic Images

Seismic images reconstruct subsurface reflectivity from field recordings, guiding exploration and reservoir monitoring. Gas chimneys are vertical anomalies caused by subsurface fluid migration. Understanding these phenomena is crucial for assessing hydrocarbon potential and avoiding drilling hazards. However, accurate detection is challenging due to strong seismic attenuation and scattering. Traditional physics-based methods are computationally expensive and sensitive to model errors, while deep learning offers efficient alternatives, yet lacks labeled datasets. In this work, we introduce \textbf{SIGMA}, a new physics-based dataset for gas chimney understanding in seismic images, featuring (i) pixel-level gas-chimney mask for detection and (ii) paired degraded and ground-truth image for enhancement. We employed physics-based methods that cover a wide range of geological settings and data acquisition conditions. Comprehensive experiments demonstrate that SIGMA serves as a challenging benchmark for gas chimney interpretation and benefits general seismic understanding.

cs.CV↗
arXiv2026

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

Video Scene Graph Generation (VidSGG) aims to represent dynamic visual content by detecting objects and modeling their temporal interactions as structured graphs. Prior studies typically target either coarse-grained box-level or fine-grained panoptic pixel-level VidSGG, often requiring task-specific architectures and multi-stage training pipelines. In this paper, we present UNO (UNified Object-centric VidSGG), a single-stage, unified framework that jointly addresses both tasks within an end-to-end architecture. UNO is designed to minimize task-specific modifications and maximize parameter sharing, enabling generalization across different levels of visual granularity. The core of UNO is an extended slot attention mechanism that decomposes visual features into object and relation slots. To ensure robust temporal modeling, we introduce object temporal consistency learning, which enforces consistent object representations across frames without relying on explicit tracking modules. Additionally, a dynamic triplet prediction module links relation slots to corresponding object pairs, capturing evolving interactions over time. We evaluate UNO on standard box-level and pixel-level VidSGG benchmarks. Results demonstrate that UNO not only achieves competitive performance across both tasks but also offers improved efficiency through a unified, object-centric design. Code is available at: https://github.com/Fsoft-AIC/UNO

cs.CV↗
arXiv2025

Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective

As embodied agents operate in increasingly complex environments, the ability to perceive, track, and reason about individual object instances over time becomes essential, especially in tasks requiring sequenced interactions with visually similar objects. In these non-Markovian settings, key decision cues are often hidden in object-specific histories rather than the current scene. Without persistent memory of prior interactions (what has been interacted with, where it has been, or how it has changed) visuomotor policies may fail, repeat past actions, or overlook completed ones. To surface this challenge, we introduce LIBERO-Mem, a non-Markovian task suite for stress-testing robotic manipulation under object-level partial observability. It combines short- and long-horizon object tracking with temporally sequenced subgoals, requiring reasoning beyond the current frame. However, vision-language-action (VLA) models often struggle in such settings, with token scaling quickly becoming intractable even for tasks spanning just a few hundred frames. We propose Embodied-SlotSSM, a slot-centric VLA framework built for temporal scalability. It maintains spatio-temporally consistent slot identities and leverages them through two mechanisms: (1) slot-state-space modeling for reconstructing short-term history, and (2) a relational encoder to align the input tokens with action decoding. Together, these components enable temporally grounded, context-aware action prediction. Experiments show Embodied-SlotSSM's baseline performance on LIBERO-Mem and general tasks, offering a scalable solution for non-Markovian reasoning in object-centric robotic policies.

cs.RO↗
arXiv2025

Learning Human Motion with Temporally Conditional Mamba

Learning human motion based on a time-dependent input signal presents a challenging yet impactful task with various applications. The goal of this task is to generate or estimate human movement that consistently reflects the temporal patterns of conditioning inputs. Existing methods typically rely on cross-attention mechanisms to fuse the condition with motion. However, this approach primarily captures global interactions and struggles to maintain step-by-step temporal alignment. To address this limitation, we introduce Temporally Conditional Mamba, a new mamba-based model for human motion generation. Our approach integrates conditional information into the recurrent dynamics of the Mamba block, enabling better temporally aligned motion. To validate the effectiveness of our method, we evaluate it on a variety of human motion tasks. Extensive experiments demonstrate that our model significantly improves temporal alignment, motion realism, and condition consistency over state-of-the-art approaches. Our project page is available at https://zquang2202.github.io/TCM.

cs.CV↗
arXiv2025

TolerantECG: A Foundation Model for Imperfect Electrocardiogram

The electrocardiogram (ECG) is an essential and effective tool for diagnosing heart diseases. However, its effectiveness can be compromised by noise or unavailability of one or more leads of the standard 12-lead recordings, resulting in diagnostic errors or uncertainty. To address these challenges, we propose TolerantECG, a foundation model for ECG signals that is robust to noise and capable of functioning with arbitrary subsets of the standard 12-lead ECG. TolerantECG training combines contrastive and self-supervised learning frameworks to jointly learn ECG signal representations alongside their corresponding knowledge-retrieval-based text report descriptions and corrupted or lead-missing signals. Comprehensive benchmarking results demonstrate that TolerantECG consistently ranks as the best or second-best performer across various ECG signal conditions and class levels in the PTB-XL dataset, and achieves the highest performance on the MIT-BIH Arrhythmia Database.

cs.LG↗
arXiv2025

DualFit: A Two-Stage Virtual Try-On via Warping and Synthesis

Virtual Try-On technology has garnered significant attention for its potential to transform the online fashion retail experience by allowing users to visualize how garments would look on them without physical trials. While recent advances in diffusion-based warping-free methods have improved perceptual quality, they often fail to preserve fine-grained garment details such as logos and printed text elements that are critical for brand integrity and customer trust. In this work, we propose DualFit, a hybrid VTON pipeline that addresses this limitation by two-stage approach. In the first stage, DualFit warps the target garment to align with the person image using a learned flow field, ensuring high-fidelity preservation. In the second stage, a fidelity-preserving try-on module synthesizes the final output by blending the warped garment with preserved human regions. Particularly, to guide this process, we introduce a preserved-region input and an inpainting mask, enabling the model to retain key areas and regenerate only where necessary, particularly around garment seams. Extensive qualitative results show that DualFit achieves visually seamless try-on results while faithfully maintaining high-frequency garment details, striking an effective balance between reconstruction accuracy and perceptual realism.

cs.CV↗
arXiv2025

EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba

Estimating human dance motion is a challenging task with various industrial applications. Recently, many efforts have focused on predicting human dance motion using either egocentric video or music as input. However, the task of jointly estimating human motion from both egocentric video and music remains largely unexplored. In this paper, we aim to develop a new method that predicts human dance motion from both egocentric video and music. In practice, the egocentric view often obscures much of the body, making accurate full-pose estimation challenging. Additionally, incorporating music requires the generated head and body movements to align well with both visual and musical inputs. We first introduce EgoAIST++, a new large-scale dataset that combines both egocentric views and music with more than 36 hours of dancing motion. Drawing on the success of diffusion models and Mamba on modeling sequences, we develop an EgoMusic Motion Network with a core Skeleton Mamba that explicitly captures the skeleton structure of the human body. We illustrate that our approach is theoretically supportive. Intensive experiments show that our method clearly outperforms state-of-the-art approaches and generalizes effectively to real-world data.

cs.CV↗