Knowledge catalogue
arXiv:2403.18149v3 Announce Type: replace Abstract: Model-predictive control (MPC) is a state-of-the-art control method for constrained robotic systems, yet deployment on resource-limited hardware rem
arXiv:2510.07926v2 Announce Type: replace Abstract: Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce o
Congrats to @thinkymachines on the release of TML-Interaction-Small and tying for the top spot on our Audio MC S2S leaderboard! 🥇 Their interaction model scores a 43.4% APR, demonstrating an impressiv
arXiv:2605.06905v1 Announce Type: new Abstract: Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by
arXiv:2505.14113v3 Announce Type: replace Abstract: Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model's predicted probability for each
arXiv:2605.07907v1 Announce Type: cross Abstract: Vision-Language Latent Diffusion Models (LDMs) (Rombach et al., 2022) provide powerful generative priors for inverse problems. However, existing LDM-b
arXiv:2605.06870v1 Announce Type: new Abstract: While many approaches to improve VQ-VAE performance focus on codebook size and utilization, the effect of dimensional collapse, where trained VQ-VAE rep
arXiv:2605.07959v1 Announce Type: new Abstract: Transformers have revolutionized machine learning and deploying attention layers in the model is increasingly standard across a myriad of applications.
arXiv:2605.07193v1 Announce Type: new Abstract: Generative modeling over discrete structures underpins applications across deep learning, from biological sequence design and code generation to large l
arXiv:2605.05732v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can acquire new capabilities through fine-tuning, but continual adaptation often leads to catastrophic forgetting
arXiv:2605.07705v1 Announce Type: cross Abstract: We give a novel logical characterization of encoder-decoder transformers, the foundational architecture for LLMs that also sees use in various setting
arXiv:2605.07665v1 Announce Type: cross Abstract: Estimating counterfactual distributions under interventions is central to treatment risk assessment and counterfactual generation tasks. Existing appr
arXiv:2510.18516v3 Announce Type: replace-cross Abstract: Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic
arXiv:2603.28113v2 Announce Type: replace Abstract: The global Lipschitz constant of a neural network is related to robustness and generalization, yet unlike in many classical models, it is not plainl
arXiv:2605.07694v1 Announce Type: cross Abstract: Single-channel speaker distance estimation has recently achieved centimeter-level accuracy in simulated environments, yet it remains unclear which com
arXiv:2605.07781v1 Announce Type: new Abstract: Explicit neural representations such as 3D Gaussian Splatting (3DGS) enable high-fidelity and real-time novel view synthesis, yet optimize for alpha-com
arXiv:2605.07210v1 Announce Type: cross Abstract: PromptReps showed that an autoregressive language model can be used directly as a retriever by prompting it to generate dense and sparse representatio
arXiv:2605.07494v1 Announce Type: new Abstract: Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi
arXiv:2605.07221v1 Announce Type: new Abstract: Adapting foundation models to medical segmentation typically requires either backbone fine-tuning or high-capacity task-specific decoders, both of which
arXiv:2605.07351v1 Announce Type: new Abstract: While Gaussian Splatting-based Feature Fields (GSFFs) have shown promise for visual localization, this paper highlights that photometrically optimized G
arXiv:2605.06785v1 Announce Type: cross Abstract: Inference-time scaling methods rely on Process Reward Models (PRMs), which are often poorly calibrated and overestimate success probabilities. We prop
arXiv:2605.08036v1 Announce Type: new Abstract: We introduce CUTS-GPR, a new method for performing numerically exact Gaussian process regression (GPR) in high-dimensional settings. The key component o
arXiv:2602.20816v3 Announce Type: replace Abstract: The core learning signal used in language model distillation is the standard Kullback-Leibler (KL) divergence between the student and teacher distri
arXiv:2605.07151v1 Announce Type: cross Abstract: Urban spatial evolution is manifested not only through horizontal expansion but also through vertical structural changes. Consequently, jointly captur
arXiv:2605.06911v1 Announce Type: new Abstract: Subseasonal-to-seasonal (S2S) temperature forecasts, spanning several weeks to a few months, are critically needed in agriculture practice, energy plann
arXiv:2605.07971v1 Announce Type: new Abstract: We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) bas
arXiv:2603.14787v2 Announce Type: replace Abstract: Pneumatically-actuated anthropomorphic robots with high degrees of freedom (DOF) offer significant potential for physical human-robot interaction. H
arXiv:2508.06805v2 Announce Type: replace Abstract: Accurate localization of organ boundaries is critical in medical imaging for segmentation, registration, surgical planning, and radiotherapy. While
arXiv:2605.07642v1 Announce Type: new Abstract: Forecasting future 3D hand pose sequences from egocentric video is essential for understanding human intention and enabling embodied applications such a
arXiv:2605.06724v1 Announce Type: cross Abstract: Denoising wearable electroencephalogram (EEG) is inherently challenging since neural activity is not only subtle but also inseparable from spectrally
arXiv:2605.06810v1 Announce Type: cross Abstract: Eye movement biometrics (EMB) use subject-specific gaze dynamics for user authentication and identification. Recent deep learning-based EMB systems ac
arXiv:2605.07888v1 Announce Type: cross Abstract: Federated Learning (FL) enables decentralised model training across distributed clients without requiring data centralisation. However, the generalisa
arXiv:2605.07565v1 Announce Type: cross Abstract: We study zeroth-order optimisation under context distributional uncertainty, a setting commonly tackled using Bayesian optimisation (BO). A prevailing
arXiv:2605.07005v1 Announce Type: cross Abstract: Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) an
arXiv:2605.07458v1 Announce Type: new Abstract: Motor unit parameters such as the innervation zone centre or the conduction velocity of the electrical potential harbour the potential to improve the fi
arXiv:2605.06875v1 Announce Type: cross Abstract: Advanced driver-assistance systems (ADAS) require neural compute engines that deliver low-latency inference under strict power and area constraints. P
arXiv:2605.07988v1 Announce Type: new Abstract: The spine plays a crucial role in the dynamic locomotion of quadrupedal animals, improving the stability, speed, and efficiency of their gait, especiall
arXiv:2601.22307v2 Announce Type: replace Abstract: We study the problem of propagating the mean and covariance of a general multivariate Gaussian distribution through a deep (residual) neural network
arXiv:2605.07839v1 Announce Type: new Abstract: Variable-order Markov models generate sequences over a finite alphabet by conditioning each symbol on the longest available suffix of the generated hist
arXiv:2605.07947v1 Announce Type: cross Abstract: The escalating complexity of modern machine learning necessitates solving challenging non-convex optimization problems, particularly in high-dimension
arXiv:2605.07398v1 Announce Type: cross Abstract: While spatiotemporal deepfake detectors achieve high AUC, our experiments reveal their susceptibility to evasion attacks. These models tend to overfit
arXiv:2605.07501v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption an
arXiv:2605.06840v1 Announce Type: new Abstract: Large language models (LLMs), especially reasoning models, generate extended chain-of-thought (CoT) reasoning that often contains explicit deliberation
arXiv:2605.07859v1 Announce Type: new Abstract: Driver cognitive distraction is a major cause of road collisions and remains difficult to detect. Unlike manual or visual distraction, cognitive distrac
arXiv:2506.14399v5 Announce Type: replace-cross Abstract: Counterfactual generation aims to simulate realistic hypothetical outcomes under causal interventions. Diffusion models have emerged as a powe
arXiv:2512.00164v2 Announce Type: replace Abstract: Verified explanations are a principled way to explain the decisions taken by neural networks, which are otherwise black-box in nature. However, thes
arXiv:2605.07703v1 Announce Type: new Abstract: This paper presents a finite-time analysis for Monte Carlo Tree Search (MCTS) in Partially Observable Markov Decision Processes (POMDPs), with probabili
arXiv:2504.11837v2 Announce Type: replace-cross Abstract: Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations. Although large l
arXiv:2605.07020v1 Announce Type: cross Abstract: Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perf
arXiv:2605.07746v1 Announce Type: cross Abstract: High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions acro
arXiv:2602.09457v2 Announce Type: replace-cross Abstract: We study online learning in the random-order model, where the multiset of loss functions is chosen adversarially but revealed in a uniformly r
arXiv:2605.06684v1 Announce Type: new Abstract: Tree-involved crashes represent a critical subset of run-off-road (ROR) collisions, often resulting in fatal or severe injuries due to high-energy impac
arXiv:2605.07607v1 Announce Type: new Abstract: Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambig
arXiv:2605.07060v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) provide a mesh-free framework for solving PDE-constrained inverse problems, but their extension to Bayesian i
arXiv:2602.13506v2 Announce Type: replace-cross Abstract: Optimizing non-convex functions is a fundamental challenge across machine learning and combinatorial optimization. We introduce and study gamm
arXiv:2605.06918v1 Announce Type: cross Abstract: Previous methods that predict system-wide travel time, predominantly grounded in graph neural networks, remain limited to typical and recurring demand
arXiv:2605.07319v1 Announce Type: cross Abstract: We introduce Flux Matching, a new paradigm for generative modeling that generalizes existing score-based models to a broader family of vector fields t
arXiv:2602.14868v2 Announce Type: replace-cross Abstract: Reinforcement learning has emerged as a powerful paradigm for unlocking reasoning capabilities in language models. However, relying on sparse
arXiv:2512.02991v2 Announce Type: replace Abstract: Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic
arXiv:2605.07812v1 Announce Type: cross Abstract: Advanced persistent threat (APT) attacks remain difficult to detect due to their stealth, adaptability, and use of legitimate system components. Prove