DebFilter: Eradicating Biases Stashed in Value
arXiv:2605.28167v1 Announce Type: new Abstract: Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising proc
Knowledge catalogue
arXiv:2605.28167v1 Announce Type: new Abstract: Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising proc
arXiv:2605.27736v1 Announce Type: cross Abstract: Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing m
arXiv:2605.27774v1 Announce Type: new Abstract: In-context learning -- performing tasks based on examples given in the prompt -- is an important capability that has emerged in large language models an
arXiv:2605.28736v1 Announce Type: new Abstract: This study presents the first evaluation of general-purpose imitation learning for surgeon-robot collaborative assistance in open surgery, targeting sut
arXiv:2605.27583v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are widely used non-invasive measurements of cardiac activity and play a central role in clinical diagnosis. Recent multimodal
arXiv:2605.28184v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models,
arXiv:2605.28693v1 Announce Type: cross Abstract: Backpropagation is the core learning mechanism underlying deep learning. However, whether and how this algorithm is implemented in the brain remains h
arXiv:2605.27878v1 Announce Type: new Abstract: Large language models produce fluent fiction, yet their creative output is widely seen as flat. We ask where this quality originates in the training and
arXiv:2510.11234v3 Announce Type: replace Abstract: Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on hand
arXiv:2605.28585v1 Announce Type: new Abstract: Communication-efficient distributed optimizers such as DiLoCo reduce synchronization costs by letting workers perform many local updates before aggregat
arXiv:2605.28226v1 Announce Type: new Abstract: Small-molecule drug discovery requires simultaneous optimization of numerous properties of candidate molecules. These properties can be investigated thr
arXiv:2605.28231v1 Announce Type: cross Abstract: We present ProgVLA, a compact vision-language-action (VLA) model designed for reliable robot manipulation under tight compute and memory budgets. The
arXiv:2605.27377v1 Announce Type: cross Abstract: We present RAG-Coding, an agentic method for automated ICD-10-CM coding. RAG-Coding orchestrates four large language model (LLM) agents and grounds th
arXiv:2605.28306v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models have emerged as a dominant paradigm for efficient LLM scaling, yet adapting them to non-English downstream tasks remai
arXiv:2605.27379v1 Announce Type: new Abstract: We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and co
arXiv:2605.28549v1 Announce Type: cross Abstract: The pursuit of humanoid athletic sprints is hindered by a scarcity of humanoid-viable kinematic reference data and the inability of existing framework
arXiv:2512.11524v3 Announce Type: replace Abstract: Fine-scale forest monitoring is essential for understanding canopy structure and its dynamics, which are key indicators of carbon stocks, biodiversi
arXiv:2605.27874v1 Announce Type: new Abstract: Most Automatic Speech Recognition (ASR) systems formulate transcription as a prediction problem over orthographic units such as characters, subwords, or
arXiv:2503.22655v2 Announce Type: replace Abstract: Training vision-language models (VLMs) typically requires large-scale, high-quality image-text pairs, but collecting or synthesizing such data is co
arXiv:2605.28779v1 Announce Type: new Abstract: Vision-language models (VLMs) generate fluent causal explanations, but current evaluations cannot distinguish linguistic plausibility from faithful caus
arXiv:2605.28348v1 Announce Type: new Abstract: Vision-language segmentation models have recently achieved strong performance by leveraging high-level semantic object categories expressed in natural l
arXiv:2605.28331v1 Announce Type: new Abstract: Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. Ho
arXiv:2605.28705v1 Announce Type: new Abstract: In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassi
arXiv:2605.27582v1 Announce Type: cross Abstract: Embodied navigation requires an agent to map language and visual observations to a stream of spatial actions that drive a real robot through environme
arXiv:2605.27767v1 Announce Type: cross Abstract: Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at
arXiv:2503.18893v2 Announce Type: replace Abstract: Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent st
arXiv:2602.21636v2 Announce Type: replace Abstract: Abridged: Clinicians commonly interpret 3D medical images by examining multiple anatomical planes rather than relying on volumetric views. In clinic
arXiv:2605.26376v1 Announce Type: cross Abstract: Hepatocellular carcinoma (HCC) is biologically heterogeneous, shaped by the interplay between hepatic functional reserve and tumor-related oncologic f
arXiv:2605.26192v1 Announce Type: cross Abstract: Protein structure generative models excel at predicting single protein static structures from sequence, but routinely fail to capture the correct conf
arXiv:2605.27116v1 Announce Type: new Abstract: Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-wor
arXiv:2601.20796v2 Announce Type: replace Abstract: Transformer-based multimodal large language models often exhibit in-context learning (ICL) abilities. Motivated by this phenomenon, we ask: how do t
arXiv:2605.27351v1 Announce Type: new Abstract: 3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generati
arXiv:2605.26601v1 Announce Type: new Abstract: Vision-language models have progressed rapidly, but Tibetan remains a severely underserved low-resource language due to the lack of reproducible trainin
arXiv:2605.26797v1 Announce Type: cross Abstract: We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden st
arXiv:2605.26933v1 Announce Type: new Abstract: Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotatio
arXiv:2605.26189v1 Announce Type: cross Abstract: Quantization-aware training (QAT) with low-bit floating-point formats enables efficient LLM deployment, yet introduces subtle failure modes invisible
arXiv:2605.26842v1 Announce Type: cross Abstract: The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to pro
arXiv:2512.19602v2 Announce Type: replace Abstract: Large-scale medical biobanks provide imaging data complemented by extensive tabular information, such as clinical measurements or demographics. Howe
arXiv:2602.10104v2 Announce Type: replace-cross Abstract: Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control
arXiv:2605.26526v1 Announce Type: new Abstract: Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an ass
arXiv:2605.27258v1 Announce Type: cross Abstract: Building state-of-the-art text-to-speech (TTS) systems typically demands millions of hours of proprietary data and complex multi-stage architectures,
arXiv:2605.26431v1 Announce Type: new Abstract: Structural probes train on Universal Dependencies (UD), which does not encode formal-syntactic abstractions such as phase boundaries or phase-internal c
arXiv:2602.00959v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far t
arXiv:2605.27009v1 Announce Type: new Abstract: Predicting human olfactory perception from molecular structure has seen remarkable progress, yet these approaches require explicit chemical structure at
arXiv:2508.05305v2 Announce Type: replace Abstract: The recently proposed Large Concept Model (LCM) generates text by predicting a sequence of sentence-level embeddings and training with either mean-s
arXiv:2601.08375v2 Announce Type: replace Abstract: Semantic segmentation of 3D geospatial point clouds is fundamental to remote sensing applications, yet domain shifts caused by regional and acquisit
arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI
arXiv:2605.27239v1 Announce Type: new Abstract: Annotation quality is difficult to sustain when campaigns span weeks or months with small annotator pools. We present a Setswana sentiment dataset of 3,
arXiv:2605.26713v1 Announce Type: cross Abstract: Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive d
arXiv:2601.05289v2 Announce Type: replace-cross Abstract: The high-dimensional complex nature of detectors makes fast calorimeter simulations a prime application for modern generative machine learning
arXiv:2605.23992v1 Announce Type: cross Abstract: Radiologist eye-tracking data provide a rich record of how experts search, compare, and accumulate evidence during image reading; yet, existing method
arXiv:2601.03191v3 Announce Type: replace-cross Abstract: Multimodal medical large language models have shown substantial progress in chest X-ray interpretation but continue to face challenges in spat
arXiv:2605.25620v1 Announce Type: new Abstract: World models enable agents to predict future dynamics conditioned on actions, making the choice of latent representation central to planning and control
arXiv:2605.25764v1 Announce Type: cross Abstract: Pathology foundation models (PFMs) have emerged as a core approach for learning transferable representations from whole slide images (WSIs), and they
arXiv:2605.24423v1 Announce Type: new Abstract: In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT
arXiv:2605.25022v1 Announce Type: cross Abstract: Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing stud
arXiv:2605.25681v1 Announce Type: cross Abstract: Designing a single molecule that modulates two targets is a promising strategy for polypharmacology, but it remains substantially harder than standard
arXiv:2605.24794v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-
arXiv:2512.04733v2 Announce Type: replace-cross Abstract: End-to-end autonomous driving (AD) systems increasingly adopt vision-language-action (VLA) models, yet they typically ignore the passenger's e
arXiv:2602.01992v4 Announce Type: replace Abstract: Analogy is a central faculty of human intelligence, enabling abstract patterns discovered in one domain to be applied to another. Despite its centra