Knowledge catalogue
arXiv:2609.37024v1 Announce Type: new Abstract: Integrating transcriptomic and electrophysiological data is essential for building multimodal foundation models for neuroscience. Patch-seq provides pai
arXiv:2609.37682v1 Announce Type: new Abstract: The rapid expansion of large-scale medical datasets and computational resources has driven significant progress in medical foundation models. Given the
arXiv:2609.36581v1 Announce Type: new Abstract: Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bound
arXiv:2609.36301v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regime
arXiv:2609.36878v1 Announce Type: new Abstract: LiDAR return intensity provides complementary surface-response cues for robotic perception and state estimation, yet many simulation pipelines omit it o
arXiv:2609.36692v1 Announce Type: cross Abstract: Matrix optimizers have emerged as a promising direction, with Muon standing out as a prominent design. Revisiting Muon through its full-Gram represent
arXiv:2609.37331v1 Announce Type: new Abstract: Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly impr
arXiv:2602.04852v3 Announce Type: replace Abstract: Linear attention offers a computationally efficient yet expressive alternative to softmax attention. However, recent empirical results indicate that
arXiv:2609.36322v1 Announce Type: cross Abstract: Chunked KV-cache compression reduces the memory and attention costs of long-context inference by compressing windows of consecutive tokens into fewer
arXiv:2609.36193v1 Announce Type: new Abstract: Learning from scientific measurements often requires aligning modalities with different spatial support and resolution. Subsurface characterization is a
arXiv:2609.38180v1 Announce Type: new Abstract: Existing 3D part decomposition methods do not necessarily partition the original shape into non-overlapping parts that collectively cover the entire sha
arXiv:2609.36872v1 Announce Type: new Abstract: Flow-matching policies can represent complex robot behaviors but remain susceptible to local errors under distribution shift at deployment. Many reinfor
arXiv:2609.37631v1 Announce Type: cross Abstract: Transformers are typically trained from random initialization, requiring all their capabilities to emerge from large-scale optimization. Recent work s
arXiv:2609.36391v1 Announce Type: cross Abstract: An ongoing challenge in sensory neuroscience is to characterize the feature dimensions encoded by cortical populations. Recent approaches probe featur
arXiv:2609.37292v1 Announce Type: new Abstract: Physical active vision allows robots to change their viewpoint when task-relevant observations become unreliable, yet existing manipulation benchmarks p
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas the
arXiv:2609.35890v1 Announce Type: new Abstract: Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to rev
arXiv:2609.37543v1 Announce Type: new Abstract: Cross-lingual zero-shot transfer and multilingual fine-tuning are promising approaches for NLP tasks such as Named Entity Recognition (NER) in low-resou
arXiv:2609.37951v1 Announce Type: new Abstract: Replacing a visible advertisement in a broadcast frame is geometrically straightforward but photometrically delicate. A pasted graphic can have the corr
arXiv:2609.37040v1 Announce Type: cross Abstract: Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly.
arXiv:2609.37759v1 Announce Type: cross Abstract: Vision-language models (VLMs) exhibit strong multimodal capabilities but remain vulnerable to backdoors implanted through poisoned fine-tuning data. E
arXiv:2609.36217v1 Announce Type: new Abstract: A deeper understanding of brain function requires a precise, structured characterization of behavior.Yet, extracting behavioral representations from vid
arXiv:2609.36417v1 Announce Type: new Abstract: Relational in-context learning (ICL) uses labeled support examples and their linked relational context to predict labels for new queries. This creates a
arXiv:2609.36720v1 Announce Type: new Abstract: Memory-dependent robotic manipulation requires policies to use information that is no longer available in the current observation. Retaining history alo
arXiv:2609.37654v1 Announce Type: new Abstract: We present a method for generating high quality materials for 3D objects entirely in texture space. We finetune a video diffusion transformer for text-g
arXiv:2609.37824v1 Announce Type: new Abstract: Transformer language models build predictions through successive residual updates, but how their representations become specific to an eventual outcome
arXiv:2609.36429v1 Announce Type: new Abstract: Predicting gene expression from H&E-stained histology images offers a scalable alternative to costly spatial transcriptomics, yet most existing methods
arXiv:2609.37339v1 Announce Type: new Abstract: General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on bounding
arXiv:2609.37731v1 Announce Type: new Abstract: Activation space and parameter space provide complementary views of model computation. Activations represent information, while weights read, transform,
arXiv:2609.36881v1 Announce Type: new Abstract: Causal foundation models (CFMs) pre-trained on data generated from various structural causal models (SCMs) have been proposed for estimating causal effe
arXiv:2609.37499v1 Announce Type: new Abstract: Historical archives are an under-used source for extending the instrumental climate record backward in time, and LLMs offer a way to extract the indices
arXiv:2609.36136v1 Announce Type: new Abstract: Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on vis
arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot te
arXiv:2602.02848v2 Announce Type: replace Abstract: Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-
arXiv:2609.31677v1 Announce Type: new Abstract: Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by
arXiv:2609.31821v1 Announce Type: new Abstract: Developing label-efficient models is a central challenge in surgical AI due to the high cost and scarcity of expert annotation. While self-supervised fo
arXiv:2609.34085v1 Announce Type: cross Abstract: Autonomous driving requires extit{world models} that can understand the physical world, reason and plan, and operate safely. In this paper, we first s
arXiv:2603.12057v3 Announce Type: replace Abstract: Coarse-guided visual generation, which synthesizes fine visual samples from degraded or low-fidelity coarse references, is essential for various rea
arXiv:2511.11257v2 Announce Type: replace-cross Abstract: The rational discovery of functional solvents remains challenging because macroscopic solvent behaviors emerge from complex many-body interact
arXiv:2609.31933v1 Announce Type: cross Abstract: Native-latent guidance is a recent paradigm for solving inverse problems with latent diffusion models. It replaces repeated evaluations of the image-s
arXiv:2507.02915v2 Announce Type: replace-cross Abstract: Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent repr
arXiv:2609.32269v1 Announce Type: cross Abstract: Agents that answer questions from compressed or retrieved memory must recognize when the evidence a query needs is no longer in memory. Benchmarks for
arXiv:2609.35615v1 Announce Type: new Abstract: Behavioral Foundation Models (BFMs) are an emerging paradigm in reinforcement learning, playing a role analogous to large language models in natural lan
arXiv:2609.33254v1 Announce Type: new Abstract: Understanding how drugs interact with protein targets is fundamental to drug discovery, drug repurposing and the early identification of promising thera
arXiv:2601.10214v3 Announce Type: replace Abstract: Camera control has been extensively studied in conditioned video generation; however, performing precisely altering the camera trajectories while fa
arXiv:2609.31812v1 Announce Type: cross Abstract: Pruning reduces the number of weights in magnetic resonance imaging (MRI) reconstruction networks. Equal sparsity, however, can retain weights with di
arXiv:2609.35407v1 Announce Type: new Abstract: Text-to-motion generation and motion-to-text captioning are two fundamental tasks in human motion modeling, both grounded in the same underlying motion-
arXiv:2609.34561v1 Announce Type: new Abstract: Motor brain-computer interfaces (BCIs) aim to decode motor intention, enabling people with paralysis to control external devices. Neural motor decoding
arXiv:2609.31938v1 Announce Type: new Abstract: Generative world models can provide visual rollouts for embodied planning, yet their feasibility on edge devices depends not only on the learned model b
arXiv:2609.32167v1 Announce Type: new Abstract: Counterfactual prediction estimates an individual's outcome under an alternative intervention given their factual observations. Such outcomes are genera
arXiv:2607.09185v2 Announce Type: replace Abstract: Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions. However, learning controllable ACWMs re
arXiv:2609.35603v1 Announce Type: new Abstract: Joint-embedding predictive architectures enable planning with latent world models, but accurate transition prediction alone does not ensure that the pla
arXiv:2609.32062v1 Announce Type: cross Abstract: Although E[dropout(x)] = x, here we show that E[LayerNorm(dropout(x))] is not equal to LayerNorm(x). Accordingly, the pattern of a Dropout layer follo
arXiv:2609.33047v1 Announce Type: new Abstract: Matrix optimizers such as Muon transform each momentum matrix through an approximate orthogonalization, typically implemented by a small number of Newto
arXiv:2609.31658v1 Announce Type: new Abstract: Ship classification from Synthetic Aperture Radar (SAR) imagery is a critical computer vision task, yet the robustness of models under deployment shifts
arXiv:2609.35362v1 Announce Type: new Abstract: Large language models (LLMs) typically generate text autoregressively (AR), predicting one token at a time. Block diffusion language models (dLLMs) inst
arXiv:2609.34792v1 Announce Type: new Abstract: Long-horizon manipulation requires robots to remember cues that are no longer in view while responding to moving objects. Yet vision-language-action (VL
arXiv:2609.34720v1 Announce Type: new Abstract: As image generation and editing technologies have progressed substantially, facial forgeries pose significant challenges to privacy and public safety. D
arXiv:2609.33060v1 Announce Type: new Abstract: Speech therapists often face difficulties diagnosing impairments due to the lack of efficient tools for transcribing speech into the International Phone
arXiv:2609.33177v1 Announce Type: cross Abstract: World-Action Models (WAMs) offer visual foresight for robotic manipulation, but pixel-space models repeatedly reconstruct entire future scenes, incurr