Knowledge catalogue
arXiv:2606.00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between gene
arXiv:2606.01260v1 Announce Type: cross Abstract: Despite being home to more than 1300 ethnic groups and 700 indigenous languages, bias in Large Language Models has not been fully studied in Indonesia
arXiv:2606.01802v1 Announce Type: cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware questio
arXiv:2606.00815v1 Announce Type: new Abstract: Electroencephalography (EEG) supports a variety of brain-computer interface (BCI) tasks ranging from brain-state monitoring to human-LLM interactions. E
arXiv:2603.11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that c
arXiv:2606.00926v1 Announce Type: cross Abstract: Mechanistic studies of sequence models often treat layerwise state encodings as architectural traits: recurrent models concentrate readable state, att
arXiv:2605.22759v2 Announce Type: replace Abstract: While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personal
arXiv:2605.31522v1 Announce Type: new Abstract: Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecul
arXiv:2605.30592v1 Announce Type: new Abstract: We study the problem of assigning a scalar score to a short trajectory window that reflects its position on an ordered continuum of predictability regim
arXiv:2510.03415v3 Announce Type: replace-cross Abstract: Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pr
arXiv:2605.31040v1 Announce Type: new Abstract: Developing effective representations for register transfer level (RTL) designs is crucial for accelerating the hardware design workflow. Existing approa
arXiv:2605.30311v1 Announce Type: cross Abstract: Digital humans are fundamental to immersive interaction, yet creating a unified model for holistic modalities, including text, audio, motion, and visu
arXiv:2605.28969v1 Announce Type: cross Abstract: If an AI agent makes decisions on a person's behalf, those decisions must align with its user. We introduce representational accuracy to measure how f
arXiv:2605.29933v1 Announce Type: new Abstract: Clustering is a fundamental problem in data science with a long-standing research history, yielding numerous insightful algorithms. Despite this progres
arXiv:2605.29350v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intens
arXiv:2506.05985v3 Announce Type: replace Abstract: A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic for
arXiv:2605.30230v1 Announce Type: new Abstract: With the rapid advancement of diffusion models, talking face generation has made remarkable progress. However, existing diffusion-based methods still re
arXiv:2605.30002v1 Announce Type: new Abstract: Cross-domain multimodal time series forecasting is a challenging task, requiring models to integrate precise numerical comprehension, cross-domain seman
arXiv:2605.28854v1 Announce Type: new Abstract: Large language models (LLMs) exhibit remarkable flexibility: they can adapt to novel tasks from in-context examples without any parameter updates, a cap
arXiv:2605.30288v1 Announce Type: new Abstract: Mid-training has become an important stage in modern LLM development, using large-scale curated mixtures to strengthen capabilities before final post-tr
arXiv:2605.29906v1 Announce Type: new Abstract: Text-to-motion (T2M) generation has broad applications in character animation, virtual avatars, and human-robot interaction. Existing methods typically
arXiv:2605.29122v1 Announce Type: new Abstract: It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clin
arXiv:2510.08722v3 Announce Type: replace-cross Abstract: Instance discrimination learns visual representations by treating different augmented views of the same image as positive pairs. While this en
arXiv:2605.29292v1 Announce Type: new Abstract: This technical report presents our solution for the CVPR 2026 UG2+ Challenge Track 3: Dynamic Object Segmentation in Turbulence (DOST). We design a trai
arXiv:2605.30351v1 Announce Type: cross Abstract: Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by chang
arXiv:2605.27843v1 Announce Type: new Abstract: An important challenge in texture recognition is the limited amount of data for training frequently found in real-world applications. In computer vision
arXiv:2605.27454v1 Announce Type: cross Abstract: X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial in
arXiv:2605.28819v1 Announce Type: cross Abstract: Parameter-efficient finetuning (PEFT) has become the standard approach for adapting large language models, yet evaluations largely emphasize downstrea
arXiv:2605.28818v1 Announce Type: new Abstract: Large language models (LLMs) have become increasingly useful computational models of human language processing, but it remains unclear whether vision-la
arXiv:2605.26282v1 Announce Type: new Abstract: Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approa
arXiv:2605.26778v1 Announce Type: new Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retri
arXiv:2605.24921v1 Announce Type: new Abstract: A central challenge in electroencephalography (EEG) foundation modeling is learning transferable representations across recordings with diverse tasks, m
arXiv:2605.25998v1 Announce Type: new Abstract: Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and
arXiv:2605.24225v1 Announce Type: new Abstract: In this paper, we introduce a model of evolution and learning in robots that co-optimizes a distribution of latent design vectors (genotypes) and a mixt
arXiv:2605.24771v1 Announce Type: cross Abstract: Classical noisy-label theory predicts that downstream performance under weak supervision is bounded above by the labeler's accuracy, implying a sharp
arXiv:2605.24077v1 Announce Type: cross Abstract: Machine learning deployments in real-world wireless communication tasks face significant generalization challenges due to location and environment-spe
arXiv:2605.24681v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine
arXiv:2603.00857v2 Announce Type: replace-cross Abstract: MultiPUFFIN is a domain-informed multimodal foundation model for predicting thermophysical properties of small molecules, addressing a critica
arXiv:2512.20063v3 Announce Type: replace Abstract: We introduce exttt{PairFlow}, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiri
arXiv:2605.24451v1 Announce Type: new Abstract: Vietnamese exhibits substantial dialectal phonetic variation across Northern, Central, and Southern regions, where identical lexical items may be realiz
arXiv:2605.24452v1 Announce Type: cross Abstract: Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tu
arXiv:2605.23454v1 Announce Type: new Abstract: Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable an
arXiv:2605.23790v1 Announce Type: new Abstract: Saliency prediction has been extensively studied in RGB images and videos as a computational model of human visual attention. In contrast, predicting sa
arXiv:2603.10067v2 Announce Type: replace-cross Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonal
arXiv:2605.23198v1 Announce Type: new Abstract: Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approac
arXiv:2605.23885v1 Announce Type: new Abstract: Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. Wh
arXiv:2605.21951v1 Announce Type: new Abstract: Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting pr
arXiv:2605.21835v1 Announce Type: cross Abstract: The synergistic interpretation of anatomical information from computed tomography (CT) and metabolic information from positron emission tomography (PE
arXiv:2605.22344v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) and diffusion models have each reached remarkable maturity: MLLMs excel at reasoning over heterogeneous multimo
arXiv:2605.21611v1 Announce Type: new Abstract: We introduce spatially grounded contextual image generation, a controllable image generation task that reframes the conditioning paradigm. Instead of su
arXiv:2605.20756v1 Announce Type: new Abstract: Preconditioned optimizers are central to language model training, but their stochastic update rules are usually treated as direct approximations to popu
arXiv:2605.20856v1 Announce Type: cross Abstract: Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entangle
arXiv:2605.20822v1 Announce Type: new Abstract: In this work, we address the challenge of Scene Change Detection (SCD), where the goal is to identify variations between two images of the same location
arXiv:2605.19821v1 Announce Type: new Abstract: Facial Expression Recognition (FER) in the wild is still challenging due to uncontrolled variations in pose, occlusion, and illumination. Most existing
arXiv:2602.02513v2 Announce Type: replace Abstract: Artificial intelligence has shown remarkable success in materials discovery and property prediction, particularly for crystalline and polymer system
arXiv:2605.19804v1 Announce Type: cross Abstract: For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic prefere
arXiv:2605.18328v1 Announce Type: new Abstract: LED Virtual Production (VP) uses large LED volumes to render backgrounds in real time, enabling in-camera visual effects but making post-shot changes la
arXiv:2603.03190v3 Announce Type: replace Abstract: During music listening, cortical activity encodes both acoustic and expectation-related information. Prior work has shown that ANN representations r
arXiv:2605.18147v1 Announce Type: new Abstract: Predictive models play a pivotal role in credit risk management, guiding critical decisions through accurate estimation of default probabilities and los