Diffusion models with classifier-free guidance (CFG) compute paired conditional and unconditional activations at each denoising step, yet existing post-training quantizers treat those branches as independent sources. This paper identifies the CFG branch space as a structured coding axis—matched activations are strongly correlated and jointly shaped by the guidance direction—and proposes Guidance-Correlation Branch Transform (GCBT), a lightweight $2\times 2$ orthogonal rotation applied per layer before activation quantization. It admits a closed-form per-layer solution, plugs into existing PTQ pipelines with negligible overhead, and offers a complementary, easy-to-adopt lever for low-bit generation fidelity.

FutureWorlds learns robotic world models by turning model-generated alternative futures into training experiences. The core idea unifies three ingredients: diverse beam search to build informative candidate trajectories, candidate-specific bounded memory to maintain diverging rollout histories, and MemSPO—a GRPO-based post-training algorithm that converts decoded trajectory rewards into group-relative advantages with history-consistent scoring. This addresses the exposure bias and token-level likelihood misalignment that plague autoregressive world models, where teacher-forcing training histories diverge from self-generated inference histories.

Feed-forward 3D reconstruction models like VGGT and $\pi^{3}$ rely on expensive quadratic global attention over long image sequences. VASC proposes a training-free sparse attention substitute that ranks block interactions by both query-key relevance and adjacent-value contrast, then tracks unserved computational demand across layers via a lightweight cross-layer memory. It achieves up to $2.29\times$ faster inference than dense VGGT while improving pose and reconstruction accuracy over prior sparse baselines.

This paper tackles video-to-speech (V2S) synthesis, where the central challenge is a one-to-many mapping: visually identical lip movements can correspond to different phonemes. The proposed Watch Your Speech (WYS) framework injects explicit textual conditioning—ground-truth text during training and lip-reader predictions at inference—into a conditional flow matching model via an attention-based fusion module. The key question is whether training-time textual guidance can outperform inference-only classifier guidance while preserving naturalness.

VIEScore2 addresses the shortcoming that most automatic image evaluators return only a scalar quality score without identifying defective regions. It introduces a unified evaluator that represents an image as a sparse $16\times 16$ text grid and jointly predicts perceptual quality, semantic consistency, and defect cell coordinates in a single autoregressive pass. By framing localization as text generation, it enables directly verifiable post-training rewards and supports heterogeneous supervision across generation and editing tasks. The practical value lies in producing human-readable, spatially grounded feedback from one model without task-specific prediction heads.

The paper solves the problem that weight-space task arithmetic is trapped in one architecture because parameter updates share no common coordinate system. Its core idea is the platonic task vector—a model-agnostic object beneath per-model task vectors—and the Universal Task Descriptor (UTD), an architecture-independent matrix of fine-tuning-induced affinity shifts that can be added or negated directly. A closed-form operator folds into the target's last layer, while a low-rank adapter fits the same objective across all layers. The work matters because it enables label-free, weight-free composition of task knowledge across six heterogeneous vision–language and audio–text families.

End-to-end autonomous driving maps raw sensors directly to control actions, yet its real-world bottleneck lies in the training ecosystem rather than model architecture alone. This survey introduces a Data-Strategy-Platform taxonomy that frames training as an interdependent system: data defines what is learnable, strategies govern how learning aligns with driving objectives, and platforms enable scalability. The authors argue the field must shift from raw data volume to value density, from isolated task-specific learners to universal foundation models, and from static offline training to closed-loop training-testing integration.

EyeTAG tackles temporal jitter in video gaze estimation by making gaze motion an explicit variable rather than an implicit deep feature. It feeds back first-order differences of its own recent predictions as a compact kinematic token, then fuses this with face and eye streams via cross-attention and a causal Transformer decoder. The result is a causal streaming model that cuts mean angular error on Gaze360 by roughly a degree and claims subject-invariant motion via translation-invariant differencing.

Foundation models often rely on spurious correlations, yet generating visual counterfactual explanations is usually slow and entangled. This paper proposes DiDAE, a gradient-free method that wraps a frozen visual foundation model in a conditional diffusion decoder and performs closed-form edits along disentangled dictionary atoms. The approach promises up to 2000× speed-ups over iterative methods while enabling targeted model repair via Counterfactual Knowledge Distillation and unsupervised discovery of shortcut directions.

Sign language machine translation remains far behind spoken-language MT because sign languages exploit simultaneous manual and non-manual channels, spatial grammar, and three-dimensional construction. This survey reviews the technical arc from isolated recognition to end-to-end translation and production, embedding every stage in sign language linguistics and deaf-community ethics. The authors argue that progress must be judged not by benchmark scores alone but by whether deaf users actually accept and understand the output, making the manuscript as much a piece of technology assessment as a call for sociotechnical reform.

UniTrackPLA tackles the problem of unifying instruction-guided navigation and dynamic person tracking—two embodied tasks traditionally handled by separate policies—within a single panoramic vision-language-action framework. Its core idea is to fuse omnidirectional perception with a shared continuous waypoint prediction space, using Panoramic-Aware Encoding to adapt perspective pretrained encoders to 360° observations and World-Action Consistency to adaptively decide when to reuse waypoint chunks or replan. This matters because it removes heading-dependent initialization constraints and offers a step toward general-purpose robots that can follow both linguistic routes and moving humans with one model.

Robotic foundation models currently rely on multi-step flow matching to generate actions, which creates a severe inference bottleneck for real-time control. This paper proposes Kinematic MeanFlow (K-MF), a one-step action policy that reformulates MeanFlow by decoupling the time derivative across two sub-intervals to accommodate the unique late-stage surge and widening spread of local acceleration in robotic velocity fields. By introducing an intermediate anchor point and a learnable partition strategy, K-MF cuts action-head latency by up to 74% while matching or exceeding the success rates of multi-step baselines across manipulation and navigation tasks.

This paper studies adversarial attacks under a shared global mean-$\ell_1$ budget with per-coordinate magnitude caps. The core idea is to add a centered, clean-gradient importance prior to the attack objective to softly guide perturbation mass toward model-sensitive regions without changing the feasible set. This matters because, under local capacity constraints, simply finding a useful gradient direction is insufficient—attackers must also decide where to spend a budget that cannot be arbitrarily concentrated. Empirically, the mechanism raises attack success by 2.52–17.70 percentage points over matched baselines across ten robust model–dataset configurations.

MorphoBranch tackles the problem of accurately quantifying fine, weakly labeled, and densely branched cellular structures—such as neuronal axons and microglial processes—from fluorescence microscopy images. The core idea is an integrated workbench that pairs a deterministic image-to-graph Morphometry Engine (multiscale ridge evidence, hysteresis segmentation, and evidence-constrained skeleton refinement) with an optional LLM-assisted Refinement Engine that translates natural-language instructions into editable, human-reviewable analysis plans. This separation of flexible interaction from deterministic computation aims to reduce operator-dependent bias while keeping morphometric workflows inspectable and reproducible.

World Action Models jointly predict future actions and video, but standard training independently corrupts actions and video with noise, creating a physical mismatch: perturbed actions imply a different visual future, yet the noised video stays tied to the original recording. CtrlWAM fixes this by executing perturbed actions in a simulator and pairing the rendered consequences with the perturbed actions for training, augmented with warped video–action noise schedules and a structured multi-agent conditioning interface. The approach targets more physically consistent and controllable world models for autonomous driving and robotic manipulation.

Lang3DSeg tackles annotation-free open-vocabulary 3D segmentation of sparse outdoor LiDAR using a point transformer backbone trained from scratch. Its core idea is to carefully curate 2D-to-3D pseudo-labels via class-priority rasterization and an instance-wise depth-gap test that truncates projected masks at the first occlusion gap, removing systematic depth-ambiguity errors before training. This matters because prior methods rely on voxel-based backbones and temporal voting to compensate for projection noise, whereas Lang3DSeg shows that a point transformer can match and exceed those results in real time when paired with cleaner single-sweep targets.

Open Set Recognition (OSR) requires models to classify known classes accurately while rejecting samples from unseen categories, which depends critically on learning compact, well-separated feature clusters. This paper proposes SmoothOperator (SmoothOP), a plug-in that adaptively sets the label smoothing coefficient for each training sample based on its prominence—an embedding-space signal measuring how clearly a sample's own class dominates its strongest competitor. By modulating smoothing sample-by-sample, SmoothOP yields tighter and better dispersed class representations, improving OSR performance across fine-grained benchmarks.

Vision-language models are increasingly used as backbones for all-in-one low-level image restoration, yet how they internally organize pixel-level perceptual representations remains unclear. This paper introduces GeoSim, a unified four-level framework that probes global similarity, local geometry, sparse feature decomposition, and topological structure across 24 tasks in autoregressive and diffusion transformer VLMs. By revealing that task representations are mechanism-centric and that cross-model agreement is primarily global rather than local, the study offers an actionable interpretability lens for designing transferable unified restoration systems.

Remote caregiving robots could help older adults age in place, but conventional motion-mapping teleoperation forces caregivers into slow, unnatural postures that cause muscle fatigue. This paper proposes a lightweight Spatio-Temporal Graph Convolutional Network (S-ST-GCN) that recognizes four single-arm daily-living actions from an RGB camera and triggers preset robot trajectories, decoupling the operator's motion from the robot's execution. A finite-state machine filters misclassifications before execution. While still a proof-of-concept, the framework offers a more intuitive alternative to direct motion-tracking teleoperation for assisting with activities of daily living.

This paper investigates the geometric structure of converged states in LLM pretraining, asking whether models converge to a common minimizer across data sources or merely a minimizer of the summed loss. The authors hypothesize that the "closeness" of task-specific minima correlates with downstream generalization, and propose the Nexus optimizer to maximize gradient similarity as a tractable proxy for closeness. Their core finding—that identical pretraining loss can mask vastly different downstream performance depending on the implicit bias toward geometric closeness—challenges the prevailing reliance on pretraining loss as the sole evaluation metric.