Knowledge catalogue
arXiv:2604.11188v1 Announce Type: cross Abstract: Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed
arXiv:2603.22558v2 Announce Type: replace Abstract: Generating synthetic populations from aggregate statistics is a core component of microsimulation, agent-based modeling, policy analysis, and privac
arXiv:2604.09552v1 Announce Type: cross Abstract: Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retri
arXiv:2604.11216v1 Announce Type: new Abstract: What values, evidence preferences, and source trust hierarchies do AI systems actually exhibit when facing structured dilemmas? We present the first lar
arXiv:2604.05795v2 Announce Type: replace Abstract: The increasing use of large language models in mental health applications calls for principled evaluation frameworks that assess alignment with psyc
arXiv:2604.09757v1 Announce Type: cross Abstract: Medical vision--language models (VLMs) have shown strong potential for medical visual question answering (VQA), yet their reasoning remains largely te
arXiv:2604.10242v1 Announce Type: new Abstract: Despite recent advances in MLLM-based medical image segmentation, existing LISA-like methods cannot reliably reject false queries and often produce hall
arXiv:2604.10923v1 Announce Type: cross Abstract: While large language model--powered agents can self-evolve by accumulating experience or by dynamically creating new assets (i.e., tools or expert age
arXiv:2604.09852v1 Announce Type: new Abstract: Reasoning models think in long, unstructured streams with no mechanism for compressing or organizing their own intermediate state. We introduce MEMENTO:
arXiv:2604.11427v1 Announce Type: cross Abstract: Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies. We propose ours, a metho
arXiv:2604.11012v1 Announce Type: new Abstract: The quality of text generated by large language models depends critically on the decoding sampling strategy. While mainstream methods such as Top-k, Top
arXiv:2601.14671v2 Announce Type: replace Abstract: Autoregressive (AR) visual generators model images as sequences of discrete tokens and are trained with a next-token likelihood objective. This stri
arXiv:2604.11589v1 Announce Type: new Abstract: Automatic evaluation using multimodal large language models (MLLMs), commonly referred to as MLLM-as-a-Judge, has been widely used to measure model perf
arXiv:2507.20997v4 Announce Type: replace-cross Abstract: In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, exis
arXiv:2604.10603v1 Announce Type: cross Abstract: Large language models are transforming all areas of academia and industry, attracting the attention of researchers, professionals, and the general pub
arXiv:2604.10147v1 Announce Type: cross Abstract: Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing mu
arXiv:2604.09744v1 Announce Type: cross Abstract: The AI agent ecosystem has converged on two protocols: the Model Context Protocol (MCP) for tool invocation and Agent-to-Agent (A2A) for single-princi
arXiv:2603.23516v2 Announce Type: replace-cross Abstract: Long-term memory is a cornerstone of human intelligence. Enabling AI to process lifetime-scale information remains a long-standing pursuit in
arXiv:2511.20577v3 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, fr
arXiv:2604.09704v1 Announce Type: new Abstract: Recent advances in reasoning-induced image quality assessment (IQA) have demonstrated the power of reinforcement learning to rank (RL2R) for training vi
arXiv:2604.09717v1 Announce Type: new Abstract: Character recognition is the fundamental part of an optical character recognition (OCR) system. Word recognition, sentence transcription, document digit
arXiv:2604.10347v1 Announce Type: new Abstract: Vision foundation models have been shown to be effective at processing satellite imagery into representations fit for downstream tasks, however, creatin
arXiv:2604.11734v1 Announce Type: cross Abstract: Closed-loop cooperative driving requires planners that generate realistic multimodal multi-agent trajectories while improving safety and traffic effic
arXiv:2604.10359v1 Announce Type: cross Abstract: Low-light image enhancement (LLIE) aims to restore natural visibility, color fidelity, and structural detail under severe illumination degradation. St
arXiv:2604.11274v1 Announce Type: new Abstract: We present mycelium-index, a streaming approximate nearest neighbor (ANN) index for high-dimensional vector spaces, inspired by the adaptive growth patt
arXiv:2603.02123v3 Announce Type: replace Abstract: The development of affective multimodal language models (MLMs) has long been constrained by a gap between low-level perception and high-level intera
arXiv:2604.10414v1 Announce Type: new Abstract: Accurate precipitation estimation is critical for flood forecasting, water resource management, and disaster preparedness. Satellite products provide gl
arXiv:2504.13818v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as the leading approach for enhancing reasoning capabilities in large langua
arXiv:2604.11230v1 Announce Type: new Abstract: In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI
arXiv:2604.10634v1 Announce Type: new Abstract: This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success
arXiv:2604.11415v1 Announce Type: new Abstract: Remote sensing understanding inherently requires multi-resolution observation, since different targets and application tasks demand different levels of
arXiv:2604.10666v1 Announce Type: cross Abstract: Dataset distillation compresses large-scale datasets into compact synthetic sets while preserving training performance, but existing methods are large
arXiv:2604.11102v1 Announce Type: new Abstract: Current multimodal large language models (MLLMs) have demonstrated remarkable capabilities in short-form video understanding, yet translating long-form
arXiv:2604.11804v1 Announce Type: new Abstract: In this work, we study Human-Object Interaction Video Generation (HOIVG), which aims to synthesize high-quality human-object interaction videos conditio
arXiv:2604.11403v1 Announce Type: cross Abstract: Analyzing unsteady fluid flows often requires access to the full distribution of possible temporal states, yet conventional PDE solvers are computatio
arXiv:2502.07114v2 Announce Type: replace-cross Abstract: Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly
arXiv:2604.11411v1 Announce Type: new Abstract: Reasoning video object segmentation predicts pixel-level masks in videos from natural-language queries that may involve implicit and temporally grounded
arXiv:2604.11587v1 Announce Type: new Abstract: This paper introduces Bidirectional Tight Informed Trees (BTIT*), an asymptotically optimal kinodynamic sampling-based motion planning algorithm that in
Cognition AI has published a technical report detailing the design methodology behind their reward system, likely related to their Devin AI software engineering agent. The report covers the performanc
arXiv:2604.09643v1 Announce Type: new Abstract: Three-dimensional (3D) handheld photoacoustic tomography typically relies on bulky and expensive external positioning sensors to correct motion artifact
arXiv:2604.11484v1 Announce Type: new Abstract: On-the-Fly Category Discovery (OCD) requires a model, trained on an offline support set, to recognize known classes while discovering new ones from an o
arXiv:2604.11061v1 Announce Type: cross Abstract: Mechanistic interpretability is often motivated for alignment auditing, where a model's verbal explanations can be absent, incomplete, or misleading.
arXiv:2604.09556v1 Announce Type: cross Abstract: Mixed-integer programming (MIP) extends linear programming by incorporating both continuous and integer decision variables, making it widely used in p
arXiv:2601.15593v2 Announce Type: replace-cross Abstract: Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent
arXiv:2604.10085v1 Announce Type: new Abstract: We propose a robust alignment technique for Standard Fundus Images (SFIs) and Ultra-Widefield Fundus Images (UWFIs), which are challenging to align due
arXiv:2604.09863v1 Announce Type: cross Abstract: The goal of domain adaptation is to make predictions for unlabeled samples from a target domain with the help of labeled samples from a different but
arXiv:2604.10475v1 Announce Type: new Abstract: Modeling household-level trip generation is fundamental to accurate demand forecasting, traffic flow estimation, and urban system planning. Existing stu
arXiv:2604.10125v1 Announce Type: new Abstract: Existing single-image 3D indoor scene generators often produce results that look visually plausible but fail to obey real-world physics, limiting their
arXiv:2604.10415v1 Announce Type: new Abstract: We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from spars
arXiv:2603.23966v3 Announce Type: replace-cross Abstract: With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate fo
arXiv:2509.21882v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other s
arXiv:2412.04272v5 Announce Type: replace-cross Abstract: In recent years, table reasoning has garnered substantial research interest, particularly regarding its integration with Large Language Models
arXiv:2604.10586v1 Announce Type: cross Abstract: This paper explores Online Continual Self-Supervised Learning (OCSSL), a scenario in which models learn from continuous streams of unlabeled, non-stat
arXiv:2507.17596v3 Announce Type: replace-cross Abstract: While end-to-end autonomous driving models show promising results, their practical deployment is often hindered by large model sizes, a relian
arXiv:2604.09824v1 Announce Type: cross Abstract: Vision language action (VLA) models enable generalist robotic agents but often exhibit language ignorance, relying on visual shortcuts and remaining i
arXiv:2512.05564v2 Announce Type: replace Abstract: Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to pro
arXiv:2602.21428v2 Announce Type: replace Abstract: Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment
arXiv:2508.19600v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, th
arXiv:2604.10188v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG). However, existing methods implicitly assume high-
arXiv:2604.10960v1 Announce Type: new Abstract: Knowledge Tracing (KT) infers a student's knowledge state from past interactions to predict future performance. Conventional Deep Learning (DL)-based KT