Knowledge catalogue
arXiv:2604.25457v1 Announce Type: new Abstract: Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion
arXiv:2604.25352v1 Announce Type: new Abstract: Current research on distributed multi-modal learning typically assumes that clients can access complete information across all modalities, which may not
arXiv:2412.08835v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) are almost universally built on a single primitive: the neighborhood. Regardless of architectural variations, message p
arXiv:2604.25126v1 Announce Type: new Abstract: Dexterous robot hands offer rich opportunities for multifunctional manipulation, where a robot must execute multiple skills in sequence while maintainin
arXiv:2601.09093v2 Announce Type: replace Abstract: Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of
arXiv:2512.05207v2 Announce Type: replace-cross Abstract: Virtual Network Embedding (VNE) is a key enabler of network slicing, yet most formulations assume that each Virtual Network Request (VNR) has
arXiv:2603.01070v2 Announce Type: replace Abstract: Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logic
arXiv:2604.25361v1 Announce Type: new Abstract: Video generation models have developed rapidly in recent years, where generating natural human motion plays a pivotal role. However, accurately evaluati
I built a TPU-native medical Q&A fine-tuning pipeline using Gemma 3 with Keras and JAX The project fine-tunes Gemma-3 on medical dialogue data from ChatDoctor and evaluates it on MedMCQA, with a large
arXiv:2604.25188v1 Announce Type: new Abstract: Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noi
arXiv:2604.24893v1 Announce Type: new Abstract: In episodic memory with natural language queries (EM-NLQ), a user may ask a question (e.g., 'Where did I place the mug?') that requires searching a long
arXiv:2604.24765v1 Announce Type: cross Abstract: P300-based brain-computer interfaces (BCIs) are widely used for communication, but population heterogeneity may alter the neural patterns available fo
arXiv:2602.15547v2 Announce Type: replace Abstract: Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpos
arXiv:2604.24927v1 Announce Type: new Abstract: Generating diverse responses is crucial for test-time scaling of large language models (LLMs), yet standard stochastic sampling mostly yields surface-le
arXiv:2604.25296v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown transformative potential in medical applications, yet their performance is hindered by conventional
arXiv:2508.07101v2 Announce Type: replace Abstract: Large reasoning models achieve strong performance through test-time scaling, but this incurs substantial computational overhead due to long decoding
arXiv:2604.24788v1 Announce Type: new Abstract: Natural gas is undoubtedly an essential component of the global energy system. Accurate short-term forecasting of natural gas price is challenging due t
arXiv:2604.25665v1 Announce Type: new Abstract: Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document
arXiv:2604.25130v1 Announce Type: new Abstract: Evaluating long document summaries remains the primary bottleneck in summarization research. Existing metrics correlate weakly with human judgments and
arXiv:2604.25578v1 Announce Type: new Abstract: We present Marco-MoE, a suite of fully open multilingual sparse Mixture-of-Experts (MoE) models. Marco-MoE features a highly sparse design in which only
arXiv:2604.25152v1 Announce Type: cross Abstract: We present MGTEVAL, an extensible platform for systematic evaluation of Machine-Generated Text (MGT) detectors. Despite rapid progress in MGT detectio
arXiv:2512.07348v2 Announce Type: replace Abstract: In controllable image generation, synthesizing coherent and consistent images from multiple reference inputs, i.e., Multi-Image Composition (MICo),
arXiv:2603.19874v3 Announce Type: replace-cross Abstract: Loss functions play a central role in supervised classification. Cross-entropy (CE) is widely used, whereas the mean absolute error (MAE) loss
arXiv:2510.22102v2 Announce Type: replace-cross Abstract: While Multimodal Large Language Models (MLLMs) excel at general vision-language tasks, precise coordinate prediction remains a significant cha
arXiv:2602.05330v2 Announce Type: replace Abstract: Comprehensive panoramic scene understanding is critical for immersive applications, yet it remains challenging due to the scarcity of high-resolutio
arXiv:2604.25276v1 Announce Type: new Abstract: Video Temporal Grounding (VTG), the task of localizing video segments from text queries, struggles in open-world settings due to limited dataset scale a
arXiv:2604.25444v1 Announce Type: new Abstract: Large Language Models (LLMs) often fail to utilize their latent reasoning capabilities due to a distributional mismatch between ambiguous human inquirie
arXiv:2604.00860v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a central post-training paradigm for improving the reasoning capabilities of large
arXiv:2604.25441v1 Announce Type: cross Abstract: Commercial TTS systems produce near-native Indic audio, but the best open-source bases (Chatterbox, Indic Parler-TTS, IndicF5) trail them on measured
arXiv:2604.25642v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined b
arXiv:2604.25154v1 Announce Type: new Abstract: Tabular Foundation Models (TFMs) achieve state-of-the-art zero-shot accuracy on small tabular datasets by meta-learning over synthetic data-generating p
arXiv:2604.25688v1 Announce Type: new Abstract: Binary spike coding enables sparse and event-driven computation in spiking neural networks (SNNs), yet its 1-bit-per-timestep representation fundamental
arXiv:2604.25325v1 Announce Type: cross Abstract: Modern Text-to-SQL systems generate multiple candidate SQL queries and rank them to judge a final prediction. However, existing methods face two limit
arXiv:2604.25304v1 Announce Type: new Abstract: Tree ensembles are widely used in industrial machine learning due to their strong predictive performance and efficient training procedures. However, as
arXiv:2604.25917v1 Announce Type: cross Abstract: Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states
arXiv:2504.11349v3 Announce Type: replace Abstract: The demand for high-quality medical imaging in clinical practice and assisted diagnosis has made 3D image reconstruction in radiological imaging a k
arXiv:2604.25655v1 Announce Type: cross Abstract: Nonlinear dynamical systems with regime transitions are typically described by ordinary differential equations with jumping parameters parameters. Tra
arXiv:2510.10150v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language M
arXiv:2506.20941v3 Announce Type: replace Abstract: Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, o
arXiv:2604.25315v1 Announce Type: new Abstract: Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly al
arXiv:2603.01421v2 Announce Type: replace-cross Abstract: Automated scientific discovery with large language models is transforming the research lifecycle from ideation to experimentation, yet existin
arXiv:2602.10750v2 Announce Type: replace-cross Abstract: The growing sophistication of modern malware and phishing campaigns has diminished the effectiveness of traditional signature-based intrusion
arXiv:2604.25367v1 Announce Type: new Abstract: In this paper, we present Self-DACE++, an improved unsupervised and lightweight framework for Low-Light Image Enhancement (LLIE), building upon our prev
SenseNova U1 is a new series of native multimodal models that unifies multimodal understanding, reasoning, and generation within a monolithic architecture, marking a fundamental paradigm shift in mult
arXiv:2604.25065v1 Announce Type: new Abstract: Object recognition (OR) in humans relies heavily on shape cues and the ability to recognize objects across varying 3D viewpoints. Unlike humans, deep ne
arXiv:2604.25181v1 Announce Type: new Abstract: Neural operators have emerged as powerful data-driven surrogates for learning solution operators of parametric partial differential equations (PDEs). Ho
arXiv:2411.16073v3 Announce Type: replace-cross Abstract: Inspired by the Well-initialized Lottery Ticket Hypothesis (WLTH), we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework fo
arXiv:2512.09923v2 Announce Type: replace Abstract: Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction of
arXiv:2604.24947v1 Announce Type: new Abstract: With the rise of mobile video consumption on diverse handheld display resolutions and orientation modes, altering videos to aspect ratios poses challeng
arXiv:2506.23690v2 Announce Type: replace Abstract: Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arb
arXiv:2604.25904v1 Announce Type: new Abstract: Identity teacher forcing (ITF) enables stable training of deterministic recurrent surrogates for chaotic dynamical systems and has been highly effective
arXiv:2604.25491v1 Announce Type: new Abstract: Current watermark removal methods are evaluated on two axes: attack success rate and perceptual quality. We show this is insufficient. While state-of-th
arXiv:2604.25299v1 Announce Type: new Abstract: Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following ta
arXiv:2604.25898v1 Announce Type: new Abstract: Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on prev
arXiv:2511.14183v3 Announce Type: replace Abstract: Digital images are often degraded by soft effects such as lens flare, haze, shadows, and reflections, which reduce aesthetics even though the underl
arXiv:2604.25334v1 Announce Type: new Abstract: Imbalanced classification remains a pervasive challenge in machine learning, particularly when minority samples are too scarce to provide a robust discr
arXiv:2604.25570v1 Announce Type: new Abstract: Spiking Transformers have shown strong potential for long-range visual modeling through spike-driven self-attention. However, their quadratic token inte
arXiv:2604.25235v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability.
arXiv:2604.03472v2 Announce Type: replace Abstract: Co-evolutionary self-play, where one language model generates problems and another solves them, promises autonomous curriculum learning without huma
We're open-sourcing Hy-MT1.5-1.8B-1.25bit — a 440MB translation model that runs fully offline on your phone, supports 33 languages, and outperforms Google Translate. At 1.8B parameters, it matches com