Knowledge catalogue
Hi! I sometimes train models and one thing always seemed very suboptimal for me. This is VAE latent files that take much more space than original data, while VAE should compress data, not making it mo
arXiv:2610.21422v1 Announce Type: cross Abstract: Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and loca
arXiv:2610.18818v2 Announce Type: cross Abstract: Pre-trained Large Language Model (LLMs) are effective on many tasks in zero-shot and few-shot settings. For machine translation of low-resource langua
arXiv:2311.04902v3 Announce Type: replace Abstract: Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting per
arXiv:2610.20610v1 Announce Type: new Abstract: Generating novel views from limited observations requires preserving both the appearance and spatial structure of a scene. Although recent approaches ex
arXiv:2610.19508v1 Announce Type: new Abstract: We propose CktHGVAE, a heterogeneous graph variational autoencoder for transistor-level analog/mixedsignal CMOS circuits that takes not only design vari
arXiv:2610.19013v1 Announce Type: new Abstract: Current scaling law formulations suggest that increasing the number of unique samples in a dataset improves model performance, while repeated exposure t
arXiv:2610.19212v1 Announce Type: new Abstract: World models of visual information predict future image frames conditioned on given action sequences. This predicted scene evolution is driven by determ
arXiv:2610.14812v1 Announce Type: cross Abstract: Three-dimensional (3D) velocity model building (VMB) remains computationally challenging with conventional approaches and native 3D neural networks, l
arXiv:2610.20318v1 Announce Type: cross Abstract: Reinforcement-learning policies for robot locomotion can fail at deployment when operating conditions shift (e.g., rough or slippery terrain, payload
arXiv:2610.19155v1 Announce Type: new Abstract: Human demonstrations offer a scalable alternative to costly robot data collection for dexterous manipulation, but most human datasets lack force measure
arXiv:2610.19654v1 Announce Type: new Abstract: Simulated students let researchers test tutoring systems and teaching strategies before real learners are available, but only if the simulation reproduc
arXiv:2610.19315v1 Announce Type: new Abstract: Sequential screening policies must use acquired feedback effectively under a fixed experiment budget. We study acquisition-time residual adaptation: a s
arXiv:2610.19185v1 Announce Type: new Abstract: Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them.
arXiv:2610.19481v1 Announce Type: new Abstract: Wrist-worn inertial measurement units (IMUs) provide a common sensing modality for tasks ranging from activity and gesture recognition to pose estimatio
arXiv:2610.19576v1 Announce Type: new Abstract: Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains
arXiv:2610.19946v1 Announce Type: new Abstract: Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at equilibrium need no
arXiv:2610.18877v1 Announce Type: cross Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervisio
arXiv:2610.19215v1 Announce Type: new Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents c
arXiv:2610.20279v1 Announce Type: new Abstract: Part-of-speech tagging is a fundamental sequence labeling task and an important component for many downstream natural language processing applications.
arXiv:2610.19123v1 Announce Type: new Abstract: Generating novel molecules with desired properties is a central challenge in drug discovery. Although foundational work focused on de novo generation, p
arXiv:2610.16443v1 Announce Type: new Abstract: Recent world action models draw on video generation priors to jointly predict future observations and robot actions. Adapting these priors to control re
arXiv:2610.15919v1 Announce Type: cross Abstract: Supervised machine learning in high-energy physics (HEP) requires training on labeled simulations of particle collisions, which are known to be unfait
arXiv:2610.17093v1 Announce Type: new Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On
arXiv:2604.05656v2 Announce Type: replace Abstract: Vision-language-action (VLA) models with flow-matching action heads, such as {pi}0 and {pi}0.5, have become a standard recipe for generalist robot m
arXiv:2610.20104v1 Announce Type: new Abstract: Autoregressive transformers trained on limit order book (LOB) message streams are increasingly proposed as foundation models for market microstructure.
arXiv:2610.20342v1 Announce Type: new Abstract: Missing data is a pervasive challenge in machine learning, often degrading predictive performance and complicating model deployment. Most existing appro
arXiv:2610.15359v1 Announce Type: new Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified
arXiv:2610.14936v1 Announce Type: cross Abstract: Diffusion policies are increasingly used in robotic control and manipulation, vision-language-action models, and world-model-based agents. Their abili
arXiv:2610.14307v1 Announce Type: cross Abstract: We propose ConicFlow, which frames constrained sampling from a flow matching model at inference time as an optimal control problem that balances devia
arXiv:2610.18741v1 Announce Type: new Abstract: Reliable detection of pedestrians and road users is essential for the safe operation of autonomous vehicles. However, this task becomes increasingly cha
arXiv:2510.06640v3 Announce Type: replace-cross Abstract: State Space Models (SSMs) have emerged as efficient, linear-time alternatives to Transformer-Based Models (TBMs) for long-context processing.
arXiv:2610.17503v1 Announce Type: new Abstract: Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational syste
arXiv:2610.16992v1 Announce Type: new Abstract: Bayesian optimisation (BO) is a powerful framework for sample-efficient optimisation of expensive black-box functions, but its application to high-dimen
arXiv:2610.16589v1 Announce Type: new Abstract: Electroencephalography (EEG) representation learning is challenged by noisy signals, inter-subject variability, and heterogeneous electrode montages in
arXiv:2610.13239v2 Announce Type: replace Abstract: Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coo
arXiv:2508.10688v3 Announce Type: replace Abstract: Single-image novel view synthesis requires viewpoint-dependent structural changes while retaining source-scene information and inferring unobserved
arXiv:2610.16427v1 Announce Type: new Abstract: Recursive reasoning models such as the Tiny Recursive Model (TRM) iteratively refine two latent states: an answer state y, decoded into the output, and
arXiv:2610.18699v1 Announce Type: new Abstract: Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world mod
arXiv:2610.18458v1 Announce Type: new Abstract: Modern image restoration methods increasingly rely on large-scale supervised training, yet clean targets are often prohibitively difficult to obtain in
arXiv:2610.17029v1 Announce Type: new Abstract: Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing appro
arXiv:2610.18711v1 Announce Type: new Abstract: Current recipes for robot learning require massive amounts of robot demonstrations to obtain robust and adaptive policies. In this work, we introduce St
arXiv:2610.16990v1 Announce Type: new Abstract: Tabular data generation aims to synthesize realistic samples from limited observations while faithfully capturing the underlying data distribution. Tabu
arXiv:2610.15699v1 Announce Type: new Abstract: Generative modeling for tabular data has advanced to the point where models can synthesize realistic records, recover missing values, and generate sampl
arXiv:2602.16681v2 Announce Type: replace Abstract: Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundat
arXiv:2610.15035v1 Announce Type: new Abstract: Contrastive learning has become the standard paradigm for multimodal representation learning, aligning semantically matched pairs while separating misma
arXiv:2610.13917v1 Announce Type: new Abstract: A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically
arXiv:2610.12904v1 Announce Type: new Abstract: Tabular foundation models (TFMs) based on prior-data fitted networks typically use sampled hard query labels, leaving avoidable sampling variability in
arXiv:2610.13764v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) are trained to approximate the Bayesian posterior predictive distribution (PPD) of a synthetic prior, yet results ab
arXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti
arXiv:2610.12870v1 Announce Type: cross Abstract: Practical ship design requires localized refinement and performance evaluation. This paper presents a reward-directed diffusion framework for localize
arXiv:2610.12638v1 Announce Type: cross Abstract: Day-ahead electricity forecasts can help building operators schedule heating, ventilation, and other services around anticipated demand. Choosing a fo
arXiv:2610.12898v1 Announce Type: new Abstract: In continuous diffusion language models (DLMs), latents generated by the diffusion prior are mapped almost deterministically to tokens, either by a deco
arXiv:2610.13818v1 Announce Type: new Abstract: Representations of supervised datasets support higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. However,
arXiv:2610.13341v1 Announce Type: new Abstract: Mamba-3 introduces input-dependent rotations into recurrent state updates, but their contribution beyond state retention remains unclear. We interpret t
arXiv:2610.10846v1 Announce Type: new Abstract: The diversity of robot embodiments and action spaces makes it challenging to build robot world models that generalize across different embodiments. We i
arXiv:2610.12235v1 Announce Type: new Abstract: AI research agents automate the cycle of proposing, implementing, and evaluating experiments, opening a path toward recursive self-improvement. Yet thei
arXiv:2512.17302v2 Announce Type: replace Abstract: We propose a generative framework for producing high-quality PBR textures on a given 3D mesh. As large-scale PBR texture datasets are scarce, our ap
arXiv:2610.11761v1 Announce Type: new Abstract: The genome holds the blueprint that governs the biological properties of the cell. Consequently, advancing our knowledge of genomic function is crucial
arXiv:2610.10906v1 Announce Type: new Abstract: Human communities are governed by normative systems: shared standards that produce extit{norms} dictating acceptable behavior, enforced through communit