Knowledge catalogue
arXiv:2609.34677v1 Announce Type: cross Abstract: World models predict future observations from current experience and actions, yet prediction can depend on observations seen far in the past. Episodic
arXiv:2609.32785v1 Announce Type: cross Abstract: Domain incremental learning is essential for adapting ophthalmic deep learning models to sequential clinical domains while preserving diagnostic exper
arXiv:2503.17915v2 Announce Type: replace-cross Abstract: Real-world degraded images often contain multiple co-occurring degradation types, making composite image restoration fundamentally different f
arXiv:2609.33235v1 Announce Type: new Abstract: Implicit object properties that are difficult to directly infer from vision, such as material, container contents, or softness, can be revealed through
arXiv:2506.19065v3 Announce Type: replace Abstract: We propose Legato, a new end-to-end model for optical music recognition (OMR), a task of converting music score images to machine-readable documents
arXiv:2609.35046v1 Announce Type: new Abstract: Category-level 6D pose estimation from a single RGB-D observation is inherently under-constrained, since partial visible geometry must be interpreted to
arXiv:2609.32447v1 Announce Type: new Abstract: Learning robust and scalable finite-state tracking is fundamental to sequence processing. While linear recurrent neural networks (RNNs), linear attentio
arXiv:2609.35573v1 Announce Type: new Abstract: Feed-forward novel view synthesis reconstructs a scene from many input images in a single forward pass, yet more views do not necessarily improve perfor
arXiv:2609.35544v1 Announce Type: cross Abstract: Reliable refusal of harmful requests is essential to the safe deployment of language models. Because excessive eagerness to please users may undermine
arXiv:2609.33407v1 Announce Type: cross Abstract: De novo crystal generation (DNG) models decide where to search in composition space and how to generate structures with one set of weights. We argue t
arXiv:2609.35528v1 Announce Type: new Abstract: Rectified linear unit (ReLU) networks can suffer from dying neurons, where units with persistently negative pre-activations produce zero outputs, blocki
arXiv:2601.06641v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard F
arXiv:2609.32612v1 Announce Type: new Abstract: Finding reliable point correspondences is difficult when point clouds have low overlap or undergo non-rigid deformation. Iterative refinement can correc
arXiv:2603.01563v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requ
arXiv:2609.33663v1 Announce Type: cross Abstract: Discovering underlying symmetries from data has emerged as a crucial challenge in scientific discovery. Existing data-driven methods for symmetry disc
arXiv:2607.17511v2 Announce Type: replace Abstract: Large Time Series Foundation Models (TSFMs) demonstrate strong zero-shot forecasting capabilities across diverse domains. However, their application
arXiv:2605.06332v2 Announce Type: replace Abstract: Constructive neural routing solvers usually score the next action by matching a decoder context to candidate embeddings, leaving deterministic one-s
arXiv:2609.35297v1 Announce Type: new Abstract: Pretraining a language model takes enormous compute, and the right optimizer can save a good part of it. Muon's spectral step gives a stronger direction
listen is a great company, alfred and florian are awesome founders the problem space listen is tackling is also an amazing use case for AI, very bullish on what they will still build here! Listen Labs
arXiv:2609.34446v1 Announce Type: new Abstract: Generative models have found great success as data-driven methods of solving inverse problems. Two popular approaches work either by combining a pretrai
arXiv:2609.32103v1 Announce Type: new Abstract: Large language models can memorize private or harmful information, motivating machine unlearning methods that remove targeted knowledge while preserving
arXiv:2609.33521v1 Announce Type: new Abstract: Trust evaluation plays a critical role in cybersecurity by supporting risk mitigation and decision-making. A variety of trust evaluation methods have be
arXiv:2609.35427v1 Announce Type: new Abstract: Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many
arXiv:2609.34427v1 Announce Type: new Abstract: Scaling LLM-based optimization from textbook-scale instances to real-world, industrial tasks remains a critical open challenge. Existing approaches are
arXiv:2609.34493v1 Announce Type: new Abstract: Explicit residual connections of the form (x+f(x)), often combined with normalization layers, have become a standard strategy for training very deep neu
arXiv:2609.33383v1 Announce Type: cross Abstract: The local linear minimization oracle (Ferris and Zavriev, 1996; arXiv:2605.08850), or Local LMO, solves constrained convex problems without having to
arXiv:2502.13440v2 Announce Type: replace-cross Abstract: Prevailing bioacoustic classifiers assign species labels to fixed time-frequency windows rather than to individual vocalizations. When multipl
arXiv:2609.32517v1 Announce Type: cross Abstract: The current deep learning training paradigm employs end-to-end backpropagation, regardless of the training stage, i.e. pre-training or fine-tuning. Ho
arXiv:2609.32742v1 Announce Type: new Abstract: Video super-resolution (VSR) is an ill-posed inverse problem that aims to reconstruct a high-resolution (HR) video from a noisy, low-resolution (LR) ver
arXiv:2505.09756v2 Announce Type: replace Abstract: In multi-agent reinforcement learning (MARL) settings, agents are often heterogeneous with diverse intrinsic utility functions. In this study, we in
arXiv:2609.32854v1 Announce Type: new Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) offer a promising approach for very low power inference due to their us
arXiv:2601.13556v2 Announce Type: replace Abstract: Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing enviro
arXiv:2609.35236v1 Announce Type: new Abstract: Long-horizon agents improve solutions through sustained interaction, execution, and task feedback. Scaling studies relate performance to resources and c
arXiv:2609.34630v1 Announce Type: new Abstract: Real-world AI systems must reason about objects that are no longer visible: an AR assistant guiding a user back to an object used earlier, a household r
arXiv:2609.35536v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded
arXiv:2609.34386v1 Announce Type: cross Abstract: On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even
arXiv:2609.34218v1 Announce Type: new Abstract: Looped language models separate computational depth from parameter count by repeatedly applying the same transformer block. Adapting these models requir
arXiv:2609.33593v1 Announce Type: new Abstract: Color enhancement of 4K images must meet a quality target under a tight compute budget. Three-dimensional lookup tables (3D LUTs) dominate real-time enh
arXiv:2609.33306v1 Announce Type: new Abstract: Current Transformer-based tracking methods typically stack multiple Transformer blocks with separate parameters to model interactions between the target
arXiv:2609.34509v1 Announce Type: new Abstract: Masked diffusion language models support arbitrary-order generation, suggesting a natural way to produce diverse outputs. However, recent work argues th
arXiv:2609.31941v1 Announce Type: new Abstract: This engineering study assesses gaze-assisted data acquisition during visual screening with a Gaze Quest implementation via webcam and GC308 near infrar
arXiv:2609.33025v1 Announce Type: new Abstract: Low-rank matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommod
NVIDIA released VSS Blueprint 3.3, a framework that stitches together vision‑language models (Cosmos), LLMs (Nemotron) and retrieval‑augmented generation to convert live or recorded video into natural
arXiv:2609.35700v1 Announce Type: new Abstract: We propose a hierarchical control framework to address severe dynamic instabilities and navigational drift that arise when a two-wheeled inverted pendul
arXiv:2609.34375v1 Announce Type: new Abstract: Compact JEPA world models enable efficient latent-space planning, but low-dimensional representation trained under reward-free self-supervision must enc
arXiv:2609.34014v1 Announce Type: new Abstract: Short-term turning-movement forecasts can support signal control and corridor operations, but unconstrained neural networks may produce physically impos
arXiv:2609.33028v1 Announce Type: new Abstract: A feed-forward neural network whose weights are integers and whose activation is the truncated identity implements, neuron by neuron, the connectives of
arXiv:2609.31736v1 Announce Type: new Abstract: Acute Lymphoblastic Leukemia (ALL) patients require early, accurate detection to enable timely treatment and effective patient management. A Convolution
arXiv:2609.34895v1 Announce Type: new Abstract: Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusions. We hypothesize that this limitat
arXiv:2609.33769v1 Announce Type: new Abstract: Quantitative evaluation of generative models for radiology remains challenging. Clinically relevant structures are often small and infrequent, feature s
arXiv:2609.34491v1 Announce Type: new Abstract: Small-molecule optimization integrates medicinal-chemistry reasoning and computational evidence through iterative, multi-objective decisions. When large
arXiv:2609.33563v1 Announce Type: new Abstract: World models improve sample efficiency by training policies on imagined trajectories, but their usefulness depends on learning representations that capt
arXiv:2609.32874v1 Announce Type: cross Abstract: The first sentence of this abstract--and the introduction to these proceedings--was authored by a human, but the bulk of this document was generated b
arXiv:2609.33683v1 Announce Type: new Abstract: When should multimodal foundation models generate tokens, and when should they directly output a decision? We present MAD-Guard, a controlled study of o
arXiv:2609.31644v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely used in language-model post-training to maximize rewards assigned to individual model outputs, such as scores from
arXiv:2609.31898v1 Announce Type: cross Abstract: Humans rely on gaze, head movements, and visual cues to attend to speakers in noisy environments, yet auditory attention decoding (AAD) has been studi
arXiv:2609.34262v1 Announce Type: cross Abstract: Agentic benchmarks guide model selection and training. Yet an agent can pass a task without demonstrating the intended capability. Such outcomes const
arXiv:2609.34442v1 Announce Type: new Abstract: While an unlearned language model may no longer recall a fact directly, the fact often remains recoverable through multi-hop reasoning over related know
arXiv:2609.34309v1 Announce Type: new Abstract: Executable programs offer explicit control over how images and videos are constructed, but generating runnable code is only the beginning of visual crea
arXiv:2609.31789v1 Announce Type: cross Abstract: In this work, we explore MammoClaw, a training-free agent framework that leverages frozen MLLMs for mammography analysis. To support agentic investiga