Knowledge catalogue
arXiv:2605.31304v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons
arXiv:2602.08267v2 Announce Type: replace-cross Abstract: We study the problem of transformation inversion on general Lie groups: a datum is transformed by an unknown group element, and the goal is to
arXiv:2605.30465v1 Announce Type: new Abstract: Multi-label topic classification without labeled training data is a challenging task, specially when documents contain complex relational information. W
arXiv:2605.31586v1 Announce Type: cross Abstract: Grasping the semantics of rare constructions (form-meaning pairings) has been shown to be a challenging problem that has currently only been solved by
arXiv:2605.31598v1 Announce Type: new Abstract: Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal s
arXiv:2605.31603v1 Announce Type: cross Abstract: Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelit
arXiv:2605.31163v1 Announce Type: cross Abstract: We introduce the design-model framework: a way to derive efficient recurrent sequence maps from explicit assumptions about memory. A design model writ
arXiv:2605.30925v1 Announce Type: new Abstract: Text-to-motion generation has progressed rapidly in recent years, offering an expressive interface for animation and human-computer interaction. However
arXiv:2605.31126v1 Announce Type: cross Abstract: Can a language model improve from plain text sampled from itself, with no prompts, no teacher, no verifier, and no reward model? Yes, but only when th
arXiv:2605.31090v1 Announce Type: cross Abstract: Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labe
arXiv:2605.30581v1 Announce Type: cross Abstract: Industrial visual sim-to-real is often described as transferring from synthetic images to real images, but industrial deployment usually involves a br
arXiv:2601.22068v2 Announce Type: replace Abstract: Foundation models have become a dominant paradigm in machine learning, achieving remarkable performance across diverse tasks through large-scale pre
arXiv:2605.31604v1 Announce Type: new Abstract: Unified multimodal models (UMMs) aim to handle perception and generation in a single model. Yet existing UMMs still rely on a frozen, separately pretrai
arXiv:2601.18537v3 Announce Type: replace-cross Abstract: Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and env
arXiv:2605.31371v1 Announce Type: new Abstract: Sign-based and LMO-inspired optimizers have recently attracted substantial attention in deep learning due to their strong performance and low memory foo
arXiv:2602.01186v2 Announce Type: replace-cross Abstract: Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high
arXiv:2605.31192v1 Announce Type: new Abstract: Recently, thanks to the advent of Multimodal-LLMs, deepfake detectors are striving not only to be generalizable but also interpretable. We propose that
arXiv:2605.30376v1 Announce Type: cross Abstract: Modern time series architectures face a fundamental trade-off: channel-independent models scale well with increasing data volume but ignore critical i
arXiv:2509.24901v4 Announce Type: replace-cross Abstract: Although probing frozen models has become a standard evaluation paradigm, self-supervised learning in audio defaults to fine-tuning when pursu
arXiv:2605.31504v1 Announce Type: new Abstract: Multimodal models in oncology can produce accurate predictions, but accurate prediction does not reveal whether the model has learned biology that is sh
arXiv:2605.29416v1 Announce Type: cross Abstract: Vision-Language-Action models have achieved remarkable progress in robotic manipulation, yet they suffer from a critical limitation: a lack of 3D scen
arXiv:2605.29992v1 Announce Type: new Abstract: Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper present
arXiv:2605.30226v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for grounding visual-language understanding into real-world robotic manipulat
arXiv:2605.29379v1 Announce Type: new Abstract: We present BrahmicTokenizer-131K, a 131,072-vocabulary byte-level BPE tokenizer that closes the Brahmic compression gap at the 131K-vocabulary class whi
arXiv:2605.29277v1 Announce Type: cross Abstract: We present Code-QA-Bench, a fully automated framework for synthesizing repository-level code understanding benchmarks that separates genuine code comp
arXiv:2502.03805v2 Announce Type: replace Abstract: Large language models have revolutionized natural language processing but face significant challenges of high storage and runtime costs, due to the
arXiv:2510.27607v3 Announce Type: replace Abstract: Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predictin
arXiv:2605.29669v1 Announce Type: cross Abstract: Recent work in random matrix theory (RMT) has developed the notion of deterministic equivalents: typically linear surrogate models that approximate th
arXiv:2603.14315v2 Announce Type: replace Abstract: While spectral-based optimizers like Muon operate directly on the spectrum of updates, standard adaptive methods such as AdamW do not account for th
arXiv:2605.29072v1 Announce Type: new Abstract: Accurate estimation and forecasting of energy consumption are important for power-system operation, planning, and demand-side management. In practice, h
arXiv:2505.21876v2 Announce Type: replace-cross Abstract: Recent approaches for video generation with camera control often create anchor videos (i.e., rendered videos that approximate desired camera m
arXiv:2605.29980v1 Announce Type: cross Abstract: Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream
arXiv:2602.08646v2 Announce Type: replace Abstract: We propose a gradient preconditioning method that makes reward-guided generation with one-step generative models both efficient and reliable. Test-t
arXiv:2605.30232v1 Announce Type: cross Abstract: How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation
arXiv:2605.29223v1 Announce Type: new Abstract: The parameter counts of the most widely used large language models (LLMs) are often withheld by their developers, leaving model size -- a primary refere
arXiv:2605.29075v1 Announce Type: new Abstract: LLMs encode both general capabilities and domain-specific knowledge in a single set of parameters. We ask whether this capacity can be reorganized: keep
arXiv:2605.29009v1 Announce Type: cross Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth
arXiv:2605.28990v1 Announce Type: new Abstract: Functional magnetic resonance imaging (fMRI) is a powerful tool for investigating human brain function. However, the high cost of data acquisition and t
arXiv:2411.14279v2 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. However, despite showing promising per
arXiv:2605.29498v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and u
arXiv:2605.29797v1 Announce Type: new Abstract: When annotators disagree on a label, the disagreement itself carries signal -- and the number of annotators needed to capture it depends on the evaluati
arXiv:2605.29577v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adap
arXiv:2605.29862v1 Announce Type: cross Abstract: AI-driven respiratory sound classification (RSC) is promising for automated pulmonary disease detection, yet multi-site deployment is hindered by inte
arXiv:2605.29738v1 Announce Type: cross Abstract: Legal NLP benchmarks overwhelmingly evaluate a single language or aggregate tasks that differ fundamentally across jurisdictions, making cross-lingual
arXiv:2605.30280v1 Announce Type: cross Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented cap
arXiv:2605.28827v1 Announce Type: new Abstract: Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B)
arXiv:2605.30289v1 Announce Type: new Abstract: Numeric tabular datasets are the dominant data format in scientific practice, yet large language models lack native mechanisms for representing numeric
arXiv:2605.29655v1 Announce Type: new Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokeni
arXiv:2601.12500v2 Announce Type: replace Abstract: Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera
arXiv:2605.29605v1 Announce Type: new Abstract: Confidence estimation for Vision-Language-Action (VLA) models is essential for robots to perform manipulation tasks in the open world, providing crucial
arXiv:2605.29548v1 Announce Type: new Abstract: Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling alrea
arXiv:2605.27461v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies have shown promising manipulation capabilities, yet their practical impact is often limited by the reliability dem
arXiv:2602.16837v2 Announce Type: replace Abstract: Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This
arXiv:2605.27986v1 Announce Type: new Abstract: Messenger RNA (mRNA) sequences as therapeutics require optimized design to ensure efficient translation, structural stability, and minimal immunogenicit
arXiv:2605.28659v1 Announce Type: new Abstract: Biological foundation models have shown strong performance in single-cell representation learning by applying transformer architectures directly to gene
arXiv:2605.28287v1 Announce Type: new Abstract: Discovering novel stable molecules without training data remains a grand scientific challenge. Current molecular generative models are trained on large,
arXiv:2605.28640v1 Announce Type: new Abstract: Efficient inference is critical for long-context language models, where attention computation and KV-cache access dominate the cost. Recent work RAT+, i
arXiv:2605.27733v1 Announce Type: new Abstract: Training instabilities such as loss spikes are frequently the result of stochastic gradient noise. Because of rare expressions in language training data
arXiv:2604.00402v2 Announce Type: replace-cross Abstract: Developing robust models to accurately predict the trajectories of surrounding agents is fundamental to autonomous driving safety. However, mo
arXiv:2605.24302v2 Announce Type: replace Abstract: Egocentric action recognition is a challenging task due to erratic camera motion, frequent hand occlusion, and the difficulty of maintaining consist