Knowledge catalogue
arXiv:2604.09169v1 Announce Type: new Abstract: Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label s
arXiv:2604.09330v1 Announce Type: cross Abstract: Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-wo
arXiv:2604.08558v1 Announce Type: cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically
I just love the language of this study...it speaks of the shifting 'community language'...and that is so true...have you noticed the new 'community language' is 'harness', it was 'contextual prompting
arXiv:2604.08045v1 Announce Type: new Abstract: Adnexal mass evaluation via ultrasound is a challenging clinical task, often hindered by subjective interpretation and significant inter-observer variab
arXiv:2601.20524v2 Announce Type: replace Abstract: Zero-shot anomaly detection aims to detect and localise abnormal regions in the image without access to any in-domain training images. While recent
arXiv:2604.07282v1 Announce Type: cross Abstract: Automated face recognition has made rapid strides over the past decade due to the unprecedented rise of deep neural network (DNN) models that can be t
arXiv:2604.08260v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item r
arXiv:2604.08015v1 Announce Type: new Abstract: We propose a unified objective function, termed CATMIL, that augments the base segmentation loss with two auxiliary supervision terms operating at diffe
LoRA (Low-Rank Adaptation) and ControlNet are complementary but fundamentally different tools for controlling Stable Diffusion image generation. LoRA modifies a model's weights to teach it new sty...
arXiv:2604.07786v1 Announce Type: new Abstract: Talking face generation has gained significant attention as a core application of generative models. To enhance the expressiveness and realism of synthe
arXiv:2511.19365v2 Announce Type: replace-cross Abstract: Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the t
arXiv:2604.06491v1 Announce Type: cross Abstract: We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matchi
arXiv:2504.17069v2 Announce Type: replace Abstract: Autoregressive (AR) image generators are becoming increasingly popular due to their ability to produce high-quality images and their scalability. Ty
arXiv:2604.03540v2 Announce Type: replace Abstract: Although multi-step generative policies achieve strong performance in robotic manipulation by modeling multimodal action distributions, they require
arXiv:2604.07394v1 Announce Type: cross Abstract: The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. W
arXiv:2604.07292v1 Announce Type: new Abstract: Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermal-hydraulic states, including locations where physi
arXiv:2604.08301v1 Announce Type: new Abstract: The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently,
arXiv:2604.07650v1 Announce Type: cross Abstract: The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretra
arXiv:2604.07958v1 Announce Type: new Abstract: Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks c
arXiv:2604.03044v2 Announce Type: replace-cross Abstract: We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performan
arXiv:2601.11471v3 Announce Type: replace Abstract: The key-value (KV) cache is a primary memory bottleneck in Transformers. We propose Low-Rank Key-Value (LRKV) attention, which reduces KV cache memo
arXiv:2604.07664v1 Announce Type: new Abstract: Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods empl
arXiv:2604.07254v1 Announce Type: cross Abstract: Deep neural networks can predict human judgments, but this does not imply that they rely on human-like information or reveal the cues underlying those
arXiv:2503.24135v3 Announce Type: replace Abstract: Weakly supervised object localization (WSOL) methods allow training models to classify images and localize ROIs. WSOL only requires low-cost image-c
arXiv:2604.07884v1 Announce Type: new Abstract: High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory an
arXiv:2604.08003v1 Announce Type: cross Abstract: Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models
arXiv:2604.08147v1 Announce Type: cross Abstract: Recent advances in audio-visual representation learning have shown the value of combining contrastive alignment with masked reconstruction. However, j
arXiv:2604.06990v1 Announce Type: cross Abstract: Psychological stress is clinically relevant in cardio-oncology, yet it is typically assessed only through patient-reported outcome measures (PROMs) an
arXiv:2604.06374v1 Announce Type: cross Abstract: Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuo
arXiv:2604.08522v1 Announce Type: new Abstract: Video temporal grounding (VTG) is typically tackled with dataset-specific models that transfer poorly across domains and query styles. Recent efforts to
arXiv:2604.08313v1 Announce Type: new Abstract: Dense annotations, such as segmentation masks, are expensive and time-consuming to obtain, especially for 3D medical images where expert voxel-wise labe
arXiv:2503.06717v3 Announce Type: replace Abstract: Interactive segmentation uses real-time user inputs, such as mouse clicks, to iteratively refine model predictions. Although not originally designed
This paper was accepted at the Workshop on Memory for LLM-Based Agentic Systems at ICLR. Language models have consistently grown to compress more world knowledge into their parameters, but the knowled
Muse Spark is the first model from Meta's Superintelligence Labs division and the debut entry in the new Muse model family, representing a 'ground-up overhaul' of the company's AI efforts. It is ...