Knowledge catalogue
arXiv:2605.19639v1 Announce Type: new Abstract: Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a sin
arXiv:2605.19069v1 Announce Type: cross Abstract: Code-switching -- the natural alternation between two languages within a single utterance -- represents one of the most challenging and under-studied
arXiv:2605.19986v1 Announce Type: cross Abstract: Fine-grained manipulation marks a regime where global scene context no longer suffices, and success hinges on the tight coupling of local attribute gr
arXiv:2605.19771v1 Announce Type: cross Abstract: Existing imitation learning methods for end-to-end autonomous driving predominantly learn from successful demonstrations by minimizing geometric devia
arXiv:2605.20127v1 Announce Type: cross Abstract: Artificial vision models are often evaluated against the human visual cortex by measuring how accurately their internal representations predict brain
arXiv:2605.19420v1 Announce Type: new Abstract: Grounding open-ended semantic instructions into physically executable local goals is a fundamental challenge in human-robot interaction. While existing
arXiv:2605.19518v1 Announce Type: new Abstract: Generating Knowledge Graphs (KGs) remains one of the most time-consuming and labor-intensive tasks for knowledge engineers, as they need to identify sem
brain dump of how/why we use Evals to measure agents before & after shipping to prod 1. Good Evals simulate what our real users will do and encounter. They’re not really random benchmark tasks, they r
arXiv:2510.16559v5 Announce Type: replace Abstract: Engineering construction automation aims to transform natural language specifications into physically viable structures, requiring complex integrate
arXiv:2605.19711v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large languag
arXiv:2605.18781v1 Announce Type: cross Abstract: Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamic
arXiv:2605.19538v1 Announce Type: cross Abstract: CAPTCHAs are widely deployed as human verification mechanisms and frequently block intelligent agents from completing end-to-end automation in real-wo
arXiv:2605.19250v1 Announce Type: new Abstract: Modality-conflict hallucination occurs when multimodal large language models (MLLMs) prioritize erroneous textual premises over contradictory visual evi
arXiv:2605.19806v1 Announce Type: cross Abstract: This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured be
arXiv:2605.20176v1 Announce Type: new Abstract: Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has a
arXiv:2605.18769v1 Announce Type: cross Abstract: Personalized Retrieval-Augmented Generation (RAG) relies on accurately selecting user-relevant documents. In practice, existing RAG approaches often s
arXiv:2605.19758v1 Announce Type: new Abstract: The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models h
arXiv:2509.14787v2 Announce Type: replace Abstract: Manipulation in confined and cluttered environments remains a significant challenge due to partial observability and complex configuration spaces. E
arXiv:2605.18808v1 Announce Type: cross Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2
arXiv:2605.19418v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM ag
arXiv:2603.17305v2 Announce Type: replace Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness aga
arXiv:2605.19075v1 Announce Type: cross Abstract: Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video arc
arXiv:2605.19666v1 Announce Type: cross Abstract: Accurate cardiac output (CO) estimation from photoplethysmography (PPG) is promising for unobtrusive hemodynamic monitoring, but remains difficult sin
arXiv:2605.19656v1 Announce Type: new Abstract: We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by sat
arXiv:2605.19484v1 Announce Type: cross Abstract: While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workfl
arXiv:2605.20036v1 Announce Type: new Abstract: Ride-hailing platforms like DiDi Chuxing operate in highly dynamic environments where balancing driver supply and passenger demand is critical. Although
arXiv:2605.19605v1 Announce Type: new Abstract: Forests worldwide are increasingly threatened by climate change and disturbances such as fire, pests, and pathogens, creating an urgent need for scalabl
arXiv:2605.19099v1 Announce Type: new Abstract: We introduce DecisionBench, a benchmark substrate for emergent delegation in long-horizon agentic workflows. The substrate fixes a task suite (GAIA, tau
arXiv:2605.19797v1 Announce Type: new Abstract: Monocular depth estimation has improved significantly in recent years, driven by increasingly powerful models and large-scale training data. Predicted d
arXiv:2605.19966v1 Announce Type: cross Abstract: Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perpl
Did we ever learn what model won gold at the IMO from OpenAI? It was a year ago and it was called an unreleased internal general purpose model back then. Has GPT-5.5 Pro Extended caught up with whatev
arXiv:2509.21196v3 Announce Type: replace-cross Abstract: Accurately forecasting the long-term evolution of turbulence represents a grand challenge in scientific computing and is crucial for applicati
arXiv:2601.16823v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit remarkable capabilities, yet it remains unclear to what extent these reflect sophisticated recall or genu
arXiv:2605.18999v1 Announce Type: new Abstract: Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains se
arXiv:2605.18993v1 Announce Type: cross Abstract: Task vector composition has emerged as a promising paradigm for editing pre-trained models, enabling model merging through addition and unlearning thr
arXiv:2605.19779v1 Announce Type: new Abstract: We adapt split conformal prediction and adaptive conformal inference (ACI) to continuous AI agent evaluation, providing distribution-free coverage guara
arXiv:2605.18871v1 Announce Type: cross Abstract: When Large Language Models produce structured outputs such as travel plans, code solutions, or multi-step proofs, individual reasoning steps may appea
arXiv:2605.19029v1 Announce Type: new Abstract: Reliable robotic manipulation requires control policies that can accurately represent and adapt to uncertainty arising from contact-rich interactions. M
arXiv:2602.23622v2 Announce Type: replace-cross Abstract: Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate pla
arXiv:2605.18915v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-
arXiv:2605.19688v1 Announce Type: new Abstract: Document manipulation localization models achieve strong performance on public benchmarks yet fail to generalize to operational document workflows. We i
arXiv:2605.20049v1 Announce Type: cross Abstract: As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. Thi
arXiv:2605.19527v1 Announce Type: new Abstract: Occluded person re-identification focuses on matching partially visible pedestrians across multiple camera views. However, occlusions disrupt body-regio
arXiv:2605.18767v1 Announce Type: cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A f
arXiv:2605.18904v1 Announce Type: cross Abstract: Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility b
arXiv:2605.18815v1 Announce Type: new Abstract: Modern large language model (LLM) training is inherently dynamic: resource fluctuations, RLHF phase shifts, and cluster elasticity continually reshape t
arXiv:2605.19130v1 Announce Type: cross Abstract: Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal
arXiv:2605.19559v1 Announce Type: cross Abstract: The rapid development of Multimodal Large Language Models (MLLMs) has led to growing interest in egocentric video understanding, specifically the abil
arXiv:2605.19004v1 Announce Type: new Abstract: Accurately forecasting human trajectories from an egocentric perspective plays a central role in applications such as humanoid robotics, wearable sensin
arXiv:2512.23461v2 Announce Type: replace-cross Abstract: Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values
arXiv:2605.19093v1 Announce Type: new Abstract: System prompts are a central control mechanism in modern AI systems, shaping behavior across conversations, tasks, and user populations. Yet they are di
arXiv:2605.18820v1 Announce Type: cross Abstract: Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead o
arXiv:2602.04381v2 Announce Type: replace-cross Abstract: Real-time polyp segmentation is essential for early colorectal cancer detection, yet clinical deployment remains blocked by GPU dependency. We
arXiv:2605.19743v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly applied to engineering design tasks, yet existing evaluation frameworks do not adequately address mul
arXiv:2410.18856v4 Announce Type: replace Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools c
arXiv:2605.18872v1 Announce Type: cross Abstract: Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive r
arXiv:2605.18867v1 Announce Type: cross Abstract: Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex,
arXiv:2605.19506v1 Announce Type: new Abstract: First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of T
arXiv:2605.19283v1 Announce Type: cross Abstract: Sequential prediction is challenging in regimes of delayed disambiguation, where early observations are ambiguous and multiple latent explanations rem