Robotic ultrasound lacks safe, realistic simulators because physics-based phantoms and acoustic solvers exhibit a large domain gap with clinical imaging, while trial-and-error on patients is unsafe. SonoWorld proposes a three-stage pipeline that first pretrains a latent-action video diffusion model on roughly 6.9 million unlabeled clinical frames, then grounds the learned dynamics to 6-DoF probe poses via a small EM-tracked thyroid dataset, and finally distills the model into a causal autoregressive generator with selective KV-cache retention for streaming inference. The goal is to provide a data-driven interactive environment for training and evaluating robotic scanning policies without requiring per-subject pose tracking, although the achieved fidelity and limited evaluation leave its practical readiness unclear.

Medical imaging models often fail when deployed across scanners or hospitals because they overfit to domain-specific textures and appearance statistics. PhaseAT addresses this by adversarially perturbing the Fourier phase of the luminance channel while keeping the amplitude spectrum fixed, generating hard training views that stress spatial organization under matched style. By encouraging the model to ignore brittle amplitude-driven correlations and focus on stable geometric structure, PhaseAT achieves large gains on both single-source and multi-source domain generalization benchmarks.

SIEVE tackles selective unlearning in vision-language models (VLMs), where a model must forget specific sensitive image-question-answer associations about an individual while retaining permitted facts about the same person. The core idea is to suppress attention-value representations for forget examples toward zero and anchor retain-example values to a frozen reference model, coupled with sequence-level negative cross-entropy. This matters because VLMs can recover biographical information from faces, creating privacy risks, and prior methods struggle to disentangle closely related forgotten and retained knowledge without degrading utility.

Where-OPD proposes a new on-policy self-distillation paradigm for multimodal large language models. Instead of giving the teacher zoomed-in image crops, it provides textual spatial hints that identify question-relevant visual elements and their coordinates, using procedurally generated synthetic counting scenes where object locations are known by design. The student learns to match the teacher’s behavior from the raw image and question alone, and the authors claim that training on just 3,000 such synthetic scenes transfers to broad real-world perception gains across 15 benchmarks.

This paper tackles handwritten Bangla word recognition by casting it as character-level object detection rather than whole-word classification. The authors ensemble SSD-MobileNetV2 and Faster R-CNN-InceptionResNetV2 to spot individual characters and diacritics in unsegmented word images, then rearrange the predictions into text. They introduce a modified Non-Maximum Suppression and a heuristic called Preserving Necessary Overlap (PNO) to cope with the cursive matra line and overlapping diacritics that make Bangla OCR notoriously difficult.

While 3D Gaussian avatars render photorealistic humans efficiently, their animation pipelines are often throttled by costly per-frame neural inference. This paper introduces GALA, which shows that the animation outputs of diverse pretrained avatar networks can be closely approximated by an identity-shared linear blendshape basis extracted via distillation, coupled with a shallow coefficient predictor. By constructing the basis with block-local PCA under a rendering-aware metric and a strict memory budget, the method reduces CPU animation cost by up to three orders of magnitude and enables 60 fps on mobile devices with only modest quality loss.

SILSA tackles the cost and topological fragility of high-resolution 3D generation by replacing dense or sparse voxel tokens with compact sliding-window slice latents along the three canonical axes. Each of the 384 fixed tokens summarizes a local depth window, preserving cross-sectional continuity while enabling a single-stage rectified-flow generator. Topology-aware slice supervision and a Volumetric Anchor Lattice then maintain geometric and structural coherence. The paper reports large efficiency gains—over 98% fewer tokens than sparse voxelizers—and solid improvements in PSNR, coverage, and Betti error.

This work tackles street-view weather recognition under severe domain shift, where labeled training images come from generic outdoor datasets and real driving scenes are unlabeled at training time. The proposed Weather-Aware ADDA conditions the adversarial domain discriminator on predicted weather probabilities, encouraging alignment that remains sensitive to weather semantics. The idea is to enable reliable onboard camera-based perception for autonomous vehicles without requiring expensive labeled street-view data for every adverse condition.

Operational geostationary fire products like the GOES Fire Detection and Characterization (FDC) suffer from high false-alarm rates and poor nighttime recall. This study replaces the FDC's rule-based algorithm with a CatBoost gradient-boosting model trained on over 60,000 GOES ABI fire pixels labeled by VIIRS active-fire detections. By evaluating on large 2024 regions outside the training domain, the authors show that a comparatively simple ML model can substantially outperform the operational product in precision, recall, and early detection latency, especially after dark.

Continual learners that keep a task-specific adapter in every ViT block accumulate parameters linearly in the number of tasks. This paper asks which blocks should specialize, showing that exhaustive placement search traces an inverted-U curve peaking at intermediate depth, while cheap internal criteria systematically favor the deep but suboptimal layers. To sidestep expensive search, the authors propose LS-B, which observes the first few tasks through a frozen fMRI encoding model of human visual cortex and commits task-specific capacity to the blocks whose brain readouts vary most across tasks relative to their stable structure.

Autonomous driving system designers face a persistent dilemma: should they build a decomposed modular pipeline or train an end-to-end neural policy? This survey-style paper addresses that question by comparing modular, imitation-learning, reinforcement-learning, and hybrid architectures across interpretability, scalability, and robustness. Its central contribution is a practical twelve-criterion, four-dimensional framework intended to guide practitioners in selecting the right paradigm for a given deployment context.

The paper tackles a critical problem in automated image-editing evaluation: multimodal large language models (MLLMs) acting as judges may be swayed by irrelevant presentation cues rather than the edit itself. Because visual interventions can alter the very quality being assessed, the authors introduce EditJudgeBias, a counterfactual benchmark of 1,196 real samples where 13 cues are injected across four evaluation stages and rigorously verified to preserve underlying quality. They audit five judges along three dimensions—invariance to cues, agreement with humans, and pairwise stability—and show that every judge shifts beyond its own noise floor, with fabricated social proof inflating scores and display-order swaps reversing up to 60.9% of verdicts.

Hob-VL introduces a diagnostic benchmark for visually grounded Boolean reasoning, asking vision-language models to evaluate ten-literal Boolean combinations over images and to identify objects satisfying Boolean descriptions. The core idea is to pair each expression with a mechanically verified De Morgan equivalent and to test both symbolic and natural-language presentations, isolating compositional reasoning from surface memorization. It matters because real-world visual queries—warehouse checks, agricultural monitoring, medical imaging—depend on reliably combining multiple visual facts under logical constraints.

Flow Matching (FM) suffers from trajectory crossings that create high-frequency velocity targets and amplify numerical integration errors during few-step sampling. This paper proposes CoFlow, a framework that injects a repulsive contrastive drift into the forward SDE to push training trajectories away from negative samples, thereby smoothing the learned velocity field. The authors derive a simulation-free stochastic interpolant, prove that the transformation preserves the endpoint distributions when boundary terms vanish, and show consistent improvements on ImageNet 256x256 at 20 sampling steps without extra training cost.

The paper tackles misalignment in canonical Gaussian video representations caused by large global camera motion. The core idea is to precompute frame-wise affine transforms, align all GOP frames into a larger atlas space, and fit canonical Gaussians there before projecting back. This plug-in alignment step lowers the burden on temporal deformation models with essentially no extra parameters, yielding large PSNR gains on high-motion sequences.

Doppelgangers—visually similar yet geometrically distinct surfaces—routinely corrupt structure-from-motion by creating false matches in large image collections. MVDG attacks this bottleneck by repurposing the feed-forward 3D foundation model VGGT to encode arbitrary multi-view image sets in a single forward pass, then applying lightweight per-layer decoders and a confidence-based early-exit gate to classify covisible pairs. The goal is to escape the quadratic $\mathcal{O}(n^2)$ inference cost of pairwise classifiers while preserving downstream reconstruction accuracy.

Post-hoc OOD detectors routinely tune hyperparameters or fit combining rules on held-out samples from the same OOD datasets used for final evaluation. This paper shows that the standard validation protocol only prevents memorization of individual images, not memorization of dataset identity, and that most reported gains vanish when the detector is instead evaluated on truly unseen OOD datasets. The authors isolate the effect with two elegant controls and derive a closed-form expression for the inflation.

NarrativeFlow tackles language-conditioned robot manipulation by generating dense robot velocity fields through a flow-matching formulation, allowing models to train on heterogeneous cross-embodiment data without platform-specific action labels. It introduces a Narrative Delta loss that aligns intermediate representations with textual descriptions of task-relevant scene changes, along with dual subtask tokens to isolate this auxiliary objective from the primary flow-generation path. On standard benchmarks and real-world mobile manipulation tasks with an HSR robot, the method substantially outperforms sparse-keypoint baselines, though absolute success rates and reliance on large MLLM-generated captions leave room for refinement.

Ego2Act introduces a benchmark and automated evaluator for goal-directed egocentric manipulation video generation. It tests whether models can plan and execute multi-step physical tasks from a single starting image and high-level goal, spanning 110 real-world cases. Experiments reveal severe limitations in current video generators, with even the best proprietary model scoring only 64.0 on human evaluation and frequently skipping prerequisite steps or violating physical continuity.

Science teachers need to find documentary clips that illustrate abstract physics concepts like inertia or gravity, but existing retrieval systems only match literal scene descriptions. This paper formalizes concept-to-example video retrieval and proposes CDDA, a three-stage adaptation framework that anchors curriculum concepts between textual examples and sparse visual evidence from documentaries. By structuring the language space on educational texts before transferring to video, CDDA aims to bridge the abstraction gap without destroying concrete image-text alignment, offering a targeted tool for instructional video search.