Knowledge catalogue
arXiv:2609.32665v1 Announce Type: cross Abstract: ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in E
arXiv:2609.32849v1 Announce Type: new Abstract: Learning transferable representations for dynamic text-attributed graphs (DyTAGs) requires models to capture underlying interaction dynamics that persis
arXiv:2609.32502v1 Announce Type: cross Abstract: De novo 3D molecular generation jointly models molecular size, topology, and geometry. Most methods pre-sample molecular size and generate Cartesian c
arXiv:2609.33253v1 Announce Type: new Abstract: We present VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis. Existing novel view synthesis (NVS) methods fac
arXiv:2609.33935v1 Announce Type: new Abstract: Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative
arXiv:2609.32918v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly being used in scientific workflows, but their ability as agents to directly control laboratory experime
arXiv:2609.32002v1 Announce Type: cross Abstract: The rank r in LoRA is widely treated as a capacity control: a smaller rank is assumed to yield a simpler model that generalizes better. We show that,
arXiv:2609.34732v1 Announce Type: new Abstract: Representation alignment speeds up diffusion transformer training by pulling an intermediate block of the model (student) toward features of a frozen pr
arXiv:2609.34650v1 Announce Type: new Abstract: Some attention heads learn similar patterns across inputs. Reusing these patterns could reduce training cost by avoiding repeated query-key score comput
arXiv:2606.18383v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are increasingly used to study internal representations in language models (LMs), but it remains unclear when an SAE-base
arXiv:2609.34012v1 Announce Type: new Abstract: Neural PDE surrogates increasingly incorporate structural priors, yet it is often unclear whether their gains arise from physics-specific information or
arXiv:2609.34826v1 Announce Type: new Abstract: Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason primar
arXiv:2609.34159v1 Announce Type: cross Abstract: World models infer latent states of an environment to capture its underlying dynamics and predict future evolution. Many real-world environments, howe
arXiv:2609.34206v1 Announce Type: new Abstract: Latent world models offer a promising way to improve Vision-Language-Action policies by capturing the consequences of actions. However, models trained p
arXiv:2609.34212v1 Announce Type: new Abstract: Mixture-of-Depths (MoD) enables conditional computation across Transformer depth by routing only a subset of tokens through selected layers, but its ori
arXiv:2609.30840v1 Announce Type: cross Abstract: One-step generators enable high-quality visual generation with a single network evaluation, but their post-training is difficult: general implicit gen
arXiv:2609.31168v1 Announce Type: new Abstract: My doctoral work aims to explore Audio Emotion Recognition (AER) in the context of atypical listening. This research focuses on auditory hypersensitivit
arXiv:2609.30557v1 Announce Type: cross Abstract: Runtime failure monitors can use a model's internal representations to anticipate failures. We audit this monitoring strategy across two autonomous-dr
arXiv:2609.30752v1 Announce Type: new Abstract: Many deep learning approaches to RNA secondary structure prediction have recently been proposed. They typically output a weight matrix W where W_{ij} is
arXiv:2609.30818v1 Announce Type: cross Abstract: Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing m
arXiv:2609.31128v1 Announce Type: new Abstract: Frequency-based adversarial attacks have recently grown popular by exploiting spectral sensitivities shared across neural architectures. Unlike spatial
arXiv:2609.30954v1 Announce Type: new Abstract: Large language models operating in multilingual contexts must resolve target response languages early in generation, yet the causal circuitry governing
arXiv:2512.18640v3 Announce Type: replace-cross Abstract: Event cameras offer a high temporal resolution over traditional frame-based cameras, which makes them suitable for motion and structure estima
arXiv:2609.31169v1 Announce Type: cross Abstract: Multimodal Machine Translation aims to incorporate additional signal from non-textual modalities to improve translations by resolving ambiguities. Whi
arXiv:2609.30634v1 Announce Type: new Abstract: How many assignments can a language model recall before it loses track of which value belongs to which entity? We measure this limit using continuous re
arXiv:2609.30789v1 Announce Type: new Abstract: In low-data structure-activity prediction, the choice of molecular representation can matter more than the choice of predictor, and tabular foundation m
arXiv:2609.30728v1 Announce Type: new Abstract: Polarization imaging captures distinctive surface and geometric cues that benefit a wide range of vision tasks. However, real-world polarization acquisi
arXiv:2609.30288v1 Announce Type: new Abstract: In Transformer-based masked language models, attention is the primary mechanism for context mixing, but there are other ways to mix data across tokens.
arXiv:2609.30795v1 Announce Type: new Abstract: Existing human motion diffusion methods provide strong motion generation quality, and recent style transfer models can inject target style cues, but fin
arXiv:2502.19784v3 Announce Type: replace-cross Abstract: With over 500 languages in Nigeria, three languages - Hausa, Yoruba and Igbo spoken by more than 175 million people, account for about 65% of
arXiv:2609.31167v1 Announce Type: new Abstract: EEG foundation models increasingly use masked prediction to learn from unlabeled recordings, but optimizing this objective does not ensure transferable
arXiv:2609.30988v1 Announce Type: new Abstract: Real-world image super-resolution (SR) requires recovering perceptually realistic high-resolution images from complex low-resolution observations while
arXiv:2609.31025v1 Announce Type: cross Abstract: Precise, high-speed control remains challenging for robots with complex actuation dynamics. Learning directly on hardware is further constrained by th
arXiv:2609.30657v1 Announce Type: cross Abstract: Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into t
arXiv:2609.30553v1 Announce Type: new Abstract: Expensive evolutionary search does not always need an exact fitness estimate for every candidate. It often needs a reliable answer to a simpler question
arXiv:2609.30832v1 Announce Type: cross Abstract: Perceived speech decoding based on non-invasive brain-computer interface (BCI) signals has been extensively studied in recent years. Research in this
arXiv:2609.30790v1 Announce Type: new Abstract: Many temporal process learning and monitoring pipelines operate in local windows, making window-level decisions unavoidable in practice. In such setting
arXiv:2609.30924v1 Announce Type: new Abstract: Accurate and efficient pronunciation transcription is essential for preparing text-to-speech training data at scale. Existing approaches have different
arXiv:2609.31491v1 Announce Type: new Abstract: Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are poin
arXiv:2609.30436v1 Announce Type: cross Abstract: Driving world models learn rich predictive representations of the surrounding environment from visual observations, yet accurate visual prediction doe
arXiv:2609.31234v1 Announce Type: new Abstract: Problem. Ultra-high-resolution (UHR) remote sensing with vague user intents has two bottlenecks: visual tokens are expensive, and tool calling must be f
Automated lint: 17 errors, 59669 warnings, 3 info
Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss functions like cross-entropy in pre-training and distillation) and s
arXiv:2609.29397v1 Announce Type: new Abstract: Ternary (1.58-bit) weights are attractive for microcontroller-class language models, but the sub-1M-parameter regime rests mainly on isolated, single-se
arXiv:2609.29487v1 Announce Type: new Abstract: Knowledge graph completion models optimize ranking, although many downstream applications require calibrated probabilities. We present BLADE, a variatio
arXiv:2511.05841v2 Announce Type: replace-cross Abstract: Alzheimer's disease (AD) is a prevalent neurodegenerative disorder for which early detection is critical. Handwriting, which can be disrupted
arXiv:2609.28865v1 Announce Type: new Abstract: Action representation plays a central role in discrete-token vision-language-action (VLA) learning but remains underexamined. Under conventional pose-in
arXiv:2603.18612v2 Announce Type: replace Abstract: We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev an
arXiv:2509.22738v3 Announce Type: replace Abstract: In autoregressive language models, each token is sampled by conditioning on all the past tokens; the overall string has thus been sampled from the c
arXiv:2609.29330v1 Announce Type: new Abstract: Identifying the set of monitored websites in mixed encrypted traffic is challenging because an individual flow often provides only partial evidence of w
arXiv:2609.29101v1 Announce Type: new Abstract: Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain
arXiv:2609.28567v1 Announce Type: new Abstract: Scanning electron microscopy (SEM) is routinely used to characterize the microstructural changes caused by hydrogen embrittlement (HE) in structural ste
arXiv:2609.29350v1 Announce Type: new Abstract: Explicit geometric references offer a direct way to structure self-supervised representations. Existing adversarial distribution-matching formulations,
arXiv:2609.29000v1 Announce Type: new Abstract: Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failu
arXiv:2609.29383v1 Announce Type: new Abstract: Climate data downscaling is the task of increasing the spatial resolution of climate data, typically by generating fine-resolution regional climate data
arXiv:2609.07746v2 Announce Type: replace Abstract: Even though backdoors in LLMs have been a growing concern, their inner workings are still under heavy scrutiny. Trigger-based backdoors are easy to
arXiv:2609.28857v1 Announce Type: new Abstract: Scene text spotting remains challenging for arbitrarily shaped text instances such as curved signs and dense multi-oriented characters in natural images
arXiv:2609.28539v1 Announce Type: new Abstract: Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose
arXiv:2609.29755v1 Announce Type: cross Abstract: How phenotypic transformations are implemented by changes in underlying regulatory dynamics remains a central question in developmental biology. Inspi
arXiv:2609.29389v1 Announce Type: new Abstract: Foundation vision-language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulat