Knowledge catalogue
arXiv:2606.26095v1 Announce Type: cross Abstract: Most Vision-Language-Action (VLA) models build on a Vision-Language Model (VLM) backbone by attaching an action module and optimizing the full policy
arXiv:2606.24952v1 Announce Type: new Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should
arXiv:2606.25366v1 Announce Type: new Abstract: Deep-space missions need onboard autonomy that is both capable and certifiable. Rule-based autonomy is certifiable but brittle, while learned autonomy i
arXiv:2606.25123v1 Announce Type: new Abstract: Humanoid robots require whole-body controllers that are both robust and precise in contact-rich environments. While deep reinforcement learning (RL) ach
arXiv:2601.21416v2 Announce Type: replace Abstract: The generalization capabilities of robotic manipulation policies are heavily influenced by the choice of visual representations. Existing approaches
arXiv:2606.25905v1 Announce Type: new Abstract: We introduce SurgAtlas, the largest surgical video-language dataset to date, comprising 15,291 videos (2,391 hours) spanning 18 surgical specialties and
arXiv:2606.25877v1 Announce Type: new Abstract: Vision-based tactile sensors (VBTSs) enable robots to infer contact geometry and force-related cues by imaging deformation through an internal camera, y
arXiv:2606.24993v1 Announce Type: new Abstract: Sequential learning is order-dependent: from Pile-style next-token domain adaptation to instruction-SFT and DPO, N candidate sources induce N! possible
arXiv:2512.18471v2 Announce Type: replace Abstract: Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow line
arXiv:2603.28090v2 Announce Type: replace Abstract: Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry a
arXiv:2606.25086v1 Announce Type: new Abstract: Many modern Language Model (LM) pipelines return an averaged model, such as an exponential moving average of the training iterates, rather than the fina
arXiv:2606.25718v1 Announce Type: new Abstract: Zero-shot visual decoding from electroencephalography (EEG) aims to infer visual semantics from non-invasive neural recordings, but remains challenging
arXiv:2606.24997v1 Announce Type: new Abstract: Geographic implicit neural representations (INRs) learn to map any coordinate on Earth to a location embedding, implicitly encoding geospatial data into
arXiv:2606.25034v1 Announce Type: new Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversaria
arXiv:2606.23964v1 Announce Type: cross Abstract: Self-supervised learning in fluorescence microscopy often relies on 2D projections, despite the inherently three-dimensional nature of cells. We prese
arXiv:2606.24696v1 Announce Type: cross Abstract: Physics-informed surrogate models can accelerate computational fluid dynamics simulations. However, many existing methods reproduce global flow patter
arXiv:2509.14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human pre
arXiv:2606.24740v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) such as CLIP have demonstrated strong generalization across natural-image domains. However, adapting th
arXiv:2606.24464v1 Announce Type: new Abstract: Text-driven Referring Video Object Segmentation (RVOS) aims to locate and segment target objects in videos given natural language. However, existing mod
arXiv:2606.24164v1 Announce Type: cross Abstract: Recent end-to-end models for EEG-guided target speech extraction report impressive results, underscoring potential for neuro-steered hearing technolog
arXiv:2606.24779v1 Announce Type: cross Abstract: Birth defects are a major cause of fetal loss, neonatal morbidity and long-term disability. In the subset with suspected genetic etiologies, exome and
arXiv:2606.24552v1 Announce Type: new Abstract: Simulator-in-the-loop optimization offers a promising inference-time mechanism for robot manipulation. It uses a physical simulator as a backend rollout
arXiv:2606.17046v2 Announce Type: replace-cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physi
arXiv:2606.23843v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are typically pre-trained on large-scale image-text datasets to capture semantic correspondences between visual content an
arXiv:2606.24059v1 Announce Type: new Abstract: Food images often contain several visible ingredients, so assigning one dish label to an entire image hides important visual structure. This work studie
arXiv:2606.23694v1 Announce Type: new Abstract: Graph-based text classification models typically rely on local neighborhood aggregation and overlook global community structure, despite semantic docume
arXiv:2606.24214v1 Announce Type: new Abstract: Accurate pulmonary vessel segmentation remains challenging due to the sparse, tortuous, and multi-scale nature of vascular structures, where small branc
arXiv:2606.24196v1 Announce Type: new Abstract: Modern AIGC pipelines deliver high-fidelity images and videos but presuppose a well-formed creation instruction, while end users rarely articulate visua
arXiv:2606.23744v1 Announce Type: cross Abstract: Deep learning has become an important tool in computational pathology, enabling automated analysis of histopathological images. While convolutional ne
arXiv:2606.24774v1 Announce Type: new Abstract: Vision-Language Large Models (VLLMs) trained on massive crawled corpora raise pressing copyright and data-provenance concerns. These concerns are partic
arXiv:2604.00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational S
arXiv:2606.24255v1 Announce Type: cross Abstract: Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-dr
arXiv:2512.10244v2 Announce Type: replace Abstract: Semi-supervised few-shot learning (SSFSL) resembles real-world applications such as auto-annotation, as it aims to learn a model from a few labeled
arXiv:2606.24430v1 Announce Type: cross Abstract: Training of neural networks for histopathology classification tasks typically relies on data encoding into latent space, which reduces complexity and
arXiv:2606.24175v1 Announce Type: new Abstract: While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods
arXiv:2606.23754v1 Announce Type: cross Abstract: Deploying foundation models for robot control raises a central challenge: the expressive power that enables rich, multimodal perception also makes the
arXiv:2606.24742v1 Announce Type: new Abstract: Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value esti
arXiv:2603.21911v2 Announce Type: replace Abstract: Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional r
arXiv:2606.22325v1 Announce Type: new Abstract: Attention sinks, representation collapse, and norm stratification are treated as transformer-specific pathologies. We show they are not specific to atte
arXiv:2606.21938v1 Announce Type: new Abstract: Reconstructing articulated objects from sparse images requires recovering complete geometry, movable parts, and motion parameters. Recent methods typica
arXiv:2606.21395v1 Announce Type: new Abstract: Atomistic structure and natural language have long been modeled separately, with language models either calling atomistic models as tools or being fine-
arXiv:2606.23542v1 Announce Type: new Abstract: Forest imagery analysis often involves multiple tightly coupled vision tasks, which must be performed under substantial variation in geographic regions,
arXiv:2606.20680v1 Announce Type: new Abstract: A biometric verifier is often deployed with a strict false match budget, so only a narrow, low false match rate (FMR) slice of the score range is used.
arXiv:2606.22138v1 Announce Type: cross Abstract: We present BioMatrix, the first multimodal foundation model that natively integrates sequences, structures, and natural language for both molecules an
arXiv:2606.22019v1 Announce Type: new Abstract: Subliminal learning lets a student inherit a teacher's hidden trait from distillation data that never names it. We ask when such transfer can be audited
arXiv:2606.21885v1 Announce Type: new Abstract: Foundation models have achieved remarkable performance across medical question answering, imaging, and electronic health record (EHR) tasks, yet reliabl
arXiv:2606.21116v1 Announce Type: new Abstract: Proofreading--correcting segmentation errors in 3D brain reconstructions--is the rate-limiting step in synapse-resolution connectomics. We release Conne
arXiv:2606.21678v1 Announce Type: new Abstract: Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reason
arXiv:2606.20990v1 Announce Type: new Abstract: Dual-robot collaboration enables tasks that exceed the reach and payload of a single robot, such as collaboratively transporting objects across environm
arXiv:2602.21218v2 Announce Type: replace-cross Abstract: High-quality data is essential for modern machine learning, yet many valuable corpora are sensitive and cannot be freely shared. Synthetic dat
arXiv:2606.22487v1 Announce Type: new Abstract: Automated frame selection for fetal biometry remains under addressed, with most prior work targeting generic quality assessment or downstream measuremen
arXiv:2509.17390v2 Announce Type: replace Abstract: While 3D Gaussian Splatting (3DGS) has emerged as a strong representation for photorealistic rendering, its vast ecosystem of assets remains difficu
arXiv:2606.22346v1 Announce Type: cross Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow An
arXiv:2606.22932v1 Announce Type: new Abstract: Reverse-mode differentiation computes every weight gradient, writes it to memory, and only then lets the optimizer read it back. This two-phase schedule
arXiv:2602.20070v3 Announce Type: replace Abstract: We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear system
arXiv:2606.20871v1 Announce Type: new Abstract: We study how trajectory-shape diversity in demonstrations affects imitation learning (IL) performance across models, tasks, and data scales. We introduc
arXiv:2606.22917v1 Announce Type: new Abstract: Learning instability is a long-standing problem across machine learning, but it is especially acute in the overparameterized regime that defines modern
arXiv:2606.20189v2 Announce Type: replace Abstract: Leveraging Vision Foundation Models (VFMs) for camera-to-LiDAR knowledge distillation offers a promising solution to the scarcity of annotated data
arXiv:2606.22556v1 Announce Type: new Abstract: Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures.
arXiv:2606.20961v1 Announce Type: new Abstract: Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method