Knowledge catalogue
arXiv:2602.19208v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face
arXiv:2512.09292v2 Announce Type: replace-cross Abstract: The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the c
arXiv:2604.21362v1 Announce Type: new Abstract: Creative Generation (CG) leverages generative models to automatically produce advertising content that highlights product features, and it has been a si
arXiv:2604.21235v1 Announce Type: cross Abstract: Multimodal clinical records contain structured measurements and clinical notes recorded over time, offering rich temporal information about the evolut
arXiv:2603.00110v2 Announce Type: replace Abstract: The scarcity of large-scale robotic data has motivated the repurposing of foundation models from other modalities for policy learning. In this work,
arXiv:2604.21617v1 Announce Type: new Abstract: Parametric projections let analysts embed new points in real time, but input variations from measurement noise or data drift can produce unpredictable s
arXiv:2604.21870v1 Announce Type: cross Abstract: STEM education researchers are often interested in identifying moments of students' mechanistic reasoning for deeper analysis, but have limited capaci
arXiv:2604.21871v1 Announce Type: new Abstract: Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decisio
arXiv:2510.18731v2 Announce Type: replace-cross Abstract: Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degra
arXiv:2604.21836v1 Announce Type: cross Abstract: Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalitie
New episode of The Information Bottleneck is out, this time with @liuzhuang1234 (Princeton). We talked about ConvNeXt and whether architecture still matters; dataset bias and what 'good data' actually
arXiv:2604.21202v1 Announce Type: cross Abstract: Local government meetings are the most common formal channel through which residents speak directly with elected officials, contest policies, and shap
arXiv:2604.20867v1 Announce Type: cross Abstract: Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible:
arXiv:2604.21809v1 Announce Type: cross Abstract: Diffusion-based generative models have reformed generative AI, and have enabled new capabilities in the science domain, for example, generating 3D str
arXiv:2604.21728v1 Announce Type: new Abstract: Pretrained vision-language models such as CLIP exhibit strong zero-shot generalization but remain sensitive to distribution shifts. Test-time adaptation
arXiv:2604.21203v1 Announce Type: cross Abstract: We study online inference and asymptotic covariance estimation for the stochastic gradient descent (SGD) algorithm. While classical methods (such as p
arXiv:2310.02635v5 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is a promising approach for solving robotic manipulation tasks. However, it is challenging to apply the RL algorit
arXiv:2510.20505v4 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) remains brittle on multi-step questions and heterogeneous evidence sources, trading accuracy against late
arXiv:2604.21478v1 Announce Type: new Abstract: Nowadays, visual data forgery detection plays an increasingly important role in social and economic security with the rapid development of generative mo
arXiv:2601.09253v2 Announce Type: replace-cross Abstract: While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert
arXiv:2604.21256v1 Announce Type: new Abstract: Policies for Partially Observable Markov Decision Processes (POMDPs) are often designed using a nominal system model. In practice, this model can deviat
arXiv:2604.21355v1 Announce Type: new Abstract: Humanoid robots have demonstrated impressive motor skills in a wide range of tasks, yet whole-body control for humanlike long-time, dynamic fighting rem
arXiv:2604.21130v1 Announce Type: new Abstract: Autonomous Unmanned Aerial Vehicles (UAVs) have revolutionized industries through their versatility with applications including aerial surveillance, sea
arXiv:2602.11569v2 Announce Type: replace Abstract: Population synthesis is essential for individual-level simulation in transport planning and socio-economic analysis, yet remains challenging due to
arXiv:2603.07961v3 Announce Type: replace Abstract: Scene Graph Generation (SGG) structures visual scenes as graphs of objects and their relations. While Multimodal Large Language Models (MLLMs) have
arXiv:2604.21043v1 Announce Type: cross Abstract: This paper examines the strategic use of language in contemporary artificial intelligence (AI) discourse, focusing on the widespread adoption of metap
arXiv:2604.21052v1 Announce Type: cross Abstract: We build on the Visual Autoregressive Modeling (VAR) framework and formulate style transfer as conditional discrete sequence modeling in a learned lat
arXiv:2604.21395v1 Announce Type: cross Abstract: We prove that empirical risk minimisation (ERM) imposes a necessary geometric constraint on learned representations: any encoder that minimises superv
arXiv:2604.21456v1 Announce Type: new Abstract: We propose a sampling-based framework for finite-horizon trajectory and policy optimization under differentiable dynamics by casting controller design a
arXiv:2604.21324v1 Announce Type: new Abstract: Visible-infrared person re-identification (VI-ReID) enables cross-modality identity matching for all-day surveillance, yet existing methods predominantl
arXiv:2604.20569v1 Announce Type: cross Abstract: Automatic systems are increasingly used to assess the originality of responses in creative tasks. They offer a potential solution to key limitations o
arXiv:2604.21148v1 Announce Type: new Abstract: Studies on bias in Automatic Speech Recognition (ASR) tend to focus on reporting error rates for speakers of underrepresented dialects, yet less researc
arXiv:2604.21361v1 Announce Type: new Abstract: Distributed AI inference pipelines rely heavily on timestamp-based observability to understand system behavior. This work demonstrates that even small c
arXiv:2604.21349v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augme
arXiv:2604.21904v1 Announce Type: new Abstract: In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent
arXiv:2510.18457v3 Announce Type: replace Abstract: The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explore
arXiv:2604.21502v1 Announce Type: new Abstract: In real-world scenarios, continual changes in weather, illumination, and imaging conditions cause significant domain shifts, leading detectors trained o
arXiv:2604.03956v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new
arXiv:2604.21309v1 Announce Type: new Abstract: Multi-document news summarisation systems are increasingly adopted for their convenience in processing vast daily news content, making fairness across d
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often
arXiv:2604.21751v1 Announce Type: cross Abstract: LLMs have been showing limitations when it comes to cultural coverage and competence, and in some cases show regional biases such as amplifying Wester
arXiv:2505.11336v4 Announce Type: replace Abstract: Despite the growing adoption of large language models (LLMs) in academic workflows, their capabilities remain limited in supporting high-quality sci
A lot of institutions and companies won’t die because of AI. They’ll die because of their own internal inability to learn. Someone recently told me that at a big company, legal had to review and appro
arXiv:2504.02181v2 Announce Type: replace Abstract: The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such a
arXiv:2603.23089v2 Announce Type: replace Abstract: Multi-view capture systems have been an important tool in research for recording human motion under controlling conditions. Most existing systems ar
arXiv:2604.20305v1 Announce Type: new Abstract: Realizing active visual tracking with a single unified model across diverse robots is challenging, as the physical constraints and motion dynamics vary
arXiv:2604.20372v1 Announce Type: cross Abstract: We report the first systematic evidence of hallucination in AI models of fluid dynamics, demonstrated in the canonical problem of hydrodynamically uns
arXiv:2604.20199v1 Announce Type: new Abstract: Multilingual Retrieval-Augmented Generation (mRAG) leverages cross-lingual evidence to ground Large Language Models (LLMs) in global knowledge. However,
arXiv:2604.20704v1 Announce Type: cross Abstract: Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected g
arXiv:2604.19780v1 Announce Type: new Abstract: Scaling test-time compute via extended reasoning has become a key paradigm for improving the capabilities of large language models (LLMs). However, exis
arXiv:2501.18873v4 Announce Type: replace Abstract: Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful approach for aligning generative models, but its reliance on learned rew
arXiv:2604.19984v1 Announce Type: cross Abstract: Research has documented LLMs' name-based bias in hiring and salary recommendations. In this paper, we instead consider a setting where LLMs generate c
arXiv:2601.03396v2 Announce Type: replace Abstract: Procedural content generation has enabled vast virtual worlds through levels, maps, and quests, but large-scale character generation remains underex
arXiv:2602.15861v2 Announce Type: replace-cross Abstract: Text analysis of tabular data relies on two core operations: summarization for corpus-level theme extraction and tagging for row-level labelin
arXiv:2604.19856v1 Announce Type: cross Abstract: Large Language Models (LLMs) show promise for generating Register-Transfer Level (RTL) code from natural language specifications, but single-shot gene
arXiv:2603.25383v3 Announce Type: replace Abstract: CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requir
arXiv:2510.18471v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between the
arXiv:2604.20027v1 Announce Type: cross Abstract: For state-of-the-art image understanding, Vision Transformers (ViTs) have become the standard architecture but their processing diverges substantially
arXiv:2603.23694v2 Announce Type: replace Abstract: Medical image registration is a fundamental task in medical image analysis, enabling the alignment of images from different modalities or time point
arXiv:2604.20763v1 Announce Type: cross Abstract: Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristi