Knowledge catalogue
arXiv:2505.16522v3 Announce Type: replace Abstract: With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that th
arXiv:2604.16721v1 Announce Type: new Abstract: Developing neural operators that accurately predict the behavior of systems governed by partial differential equations (PDEs) across unseen parameter re
arXiv:2604.17886v1 Announce Type: new Abstract: Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental cha
arXiv:2604.16492v1 Announce Type: new Abstract: Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Tra
arXiv:2509.12539v2 Announce Type: replace-cross Abstract: We present LEAF ('Lightweight Embedding Alignment Framework'), a knowledge distillation framework for text embedding models. A key distinguish
arXiv:2604.17453v1 Announce Type: cross Abstract: Being one of the oldest and most basic problems in image processing, image denoising has seen a resurgence spurred by rapid advances in deep learning.
arXiv:2604.05002v2 Announce Type: replace Abstract: Learning from weak, proxy, or relative supervision is common when ground-truth labels are unavailable, but robustness under distribution shift remai
arXiv:2604.17197v1 Announce Type: new Abstract: Recent advances in summarization research focus on improving summary quality across multiple criteria, such as completeness, conciseness, and faithfulne
arXiv:2601.05654v3 Announce Type: replace Abstract: Estimating the persuasiveness of messages is critical in various applications, from recommender systems to safety assessment of LLMs. While it is im
Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the captio
arXiv:2506.00955v2 Announce Type: replace Abstract: Sarcasm fundamentally alters meaning through tone and context, yet detecting it in speech remains a challenge due to data scarcity. In addition, exi
arXiv:2512.12643v2 Announce Type: replace Abstract: Legal relations serve as an important analytical framework for dispute resolution in civil cases. However, legal relations in Chinese civil cases re
arXiv:2604.16382v1 Announce Type: new Abstract: Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-conte
arXiv:2506.00772v2 Announce Type: replace-cross Abstract: Recent studies have shown that supervised fine-tuning of LLMs on a small number of high-quality datasets can yield strong reasoning capabiliti
arXiv:2604.18274v1 Announce Type: new Abstract: Temporal Action Detection (TAD) in untrimmed videos is currently dominated by Transformer-based architectures. While high-performing, their quadratic co
arXiv:2512.04677v5 Announce Type: replace Abstract: Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequenti
arXiv:2604.17021v1 Announce Type: new Abstract: Video editing aims to modify input videos according to user intent. Recently, end-to-end training methods have garnered widespread attention, constructi
arXiv:2604.04815v2 Announce Type: replace Abstract: The rapid development of Large Language Models (LLMs) has transformed fake news detection and fact-checking tasks from simple classification to comp
arXiv:2507.09025v4 Announce Type: replace Abstract: We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectur
arXiv:2506.03178v2 Announce Type: replace-cross Abstract: Automated radiology report generation holds significant potential to reduce radiologists' workload and enhance diagnostic accuracy. However, g
LLMs are still not consistent judges of qualitative work, and small changes to how that work is presented affect outcomes. Better harnessing and methods (multiple judging runs with randomized orders,
arXiv:2601.16504v3 Announce Type: replace Abstract: Commonsense reasoning often involves evaluating multiple plausible interpretations rather than selecting a single atomic answer, yet most benchmarks
arXiv:2510.09354v2 Announce Type: replace Abstract: Large reasoning models exhibit long chain-of-thought reasoning with complex strategies such as backtracking and self-verification. Yet, these capabi
arXiv:2604.17428v1 Announce Type: new Abstract: As video generation models achieve unprecedented capabilities, the demand for robust video evaluation metrics becomes increasingly critical. Traditional
arXiv:2604.18258v1 Announce Type: new Abstract: While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are
arXiv:2604.16788v1 Announce Type: new Abstract: Robotic manipulation policies often degrade over extended horizons, yet existing benchmarks provide limited insight into why such failures occur. Most p
arXiv:2511.07129v3 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has emerged as a parameter-efficient approach for fine-tuning large language models. However, conventional LoRA adapters
Love this work from Aksel and the post-training team at Hugging Face! Turns out the HF ecosystem (papers, datasets, models all accessible through CLI, skills and md files) is perfect for running SOTA
arXiv:2509.11983v2 Announce Type: replace Abstract: Neural network (NN) training is inherently a large-scale matrix optimization problem, yet the matrix structure of NN parameters has long been overlo
arXiv:2604.17976v1 Announce Type: new Abstract: This paper presents ltzGLUE, the first Natural Language Understanding (NLU) benchmark for Luxembourgish (LTZ) based on the popular GLUE benchmark for En
arXiv:2511.09818v2 Announce Type: replace Abstract: Restoring 3D scenes with low-light conditions is challenging, and most existing methods depend on precomputed camera poses and scene-specific optimi
arXiv:2604.17862v1 Announce Type: new Abstract: As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based arc
arXiv:2602.10732v2 Announce Type: replace Abstract: Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-f
arXiv:2604.17470v1 Announce Type: new Abstract: Machine learning has become a powerful tool for discovering governing laws of dynamical systems from data. However, most existing approaches degrade sev
arXiv:2604.18267v1 Announce Type: new Abstract: Recent advances in semantic correspondence rely on dual-encoder architectures, combining DINOv2 with diffusion backbones. While accurate, these billion-
arXiv:2604.17090v1 Announce Type: new Abstract: Human action recognition and motion generation are two active research problems in human-centric computer vision, both aiming to align motion with textu
arXiv:2503.16549v2 Announce Type: replace Abstract: Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially
arXiv:2604.18584v1 Announce Type: cross Abstract: Mathematical problem solving remains a challenging test of reasoning for large language and multimodal models, yet existing benchmarks are limited in
arXiv:2601.03190v3 Announce Type: replace Abstract: Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approac
arXiv:2604.16929v1 Announce Type: new Abstract: The accurate extraction of scientific measurements from literature is a critical yet challenging task in AI4Science, enabling large-scale analysis and i
arXiv:2604.16421v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly evaluated on mathematical reasoning, yet their robustness to equivalent problem representations remains po
arXiv:2601.06931v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings, raising concerns about social bias driven by demog
arXiv:2604.18250v1 Announce Type: new Abstract: Accurate prognostication and risk estimation are essential for guiding clinical decision-making and optimizing patient management. While radiologist-ass
arXiv:2604.16506v1 Announce Type: cross Abstract: Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple imag
arXiv:2604.17899v1 Announce Type: new Abstract: Unlike macro-expression, micro-expression does not follow a strictly consistent mapping rule between emotions and Action Units (AUs). As a result, some
arXiv:2604.17282v1 Announce Type: new Abstract: Process-Level Reward Models (PRMs) are essential for guiding complex reasoning in large language models, yet existing PRM benchmarks cover only general
arXiv:2604.18418v1 Announce Type: new Abstract: Recent advances in deep research systems enable large language models to retrieve, synthesize, and reason over large-scale external knowledge. In medici
arXiv:2601.09853v2 Announce Type: replace Abstract: Real-world health questions from patients often unintentionally embed false assumptions or premises. In such cases, safe medical communication typic
arXiv:2601.05488v3 Announce Type: replace Abstract: Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the
arXiv:2604.17054v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) function both as visual images and as structured code that encode rich geometric and layout information, yet most method
arXiv:2602.11092v2 Announce Type: replace Abstract: Identifying where quantum models may offer practical benefits in near term quantum machine learning (QML) requires moving beyond isolated algorithmi
arXiv:2510.07739v2 Announce Type: replace Abstract: Recursive transformers reuse parameters and iterate over hidden states multiple times, decoupling compute depth from parameter depth. However, under
arXiv:2507.11687v4 Announce Type: replace-cross Abstract: Large language models excel at code generation but struggle with code linting, particularly in generalizing to unseen or evolving best practic
arXiv:2604.16425v1 Announce Type: cross Abstract: This paper presents a method for the automated collection and aggregation of unstructured data from diverse web sources, utilizing Large Language Mode
arXiv:2603.02618v3 Announce Type: replace Abstract: Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in o
arXiv:2602.16144v3 Announce Type: replace Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical
arXiv:2512.21510v2 Announce Type: replace-cross Abstract: Real-world multi-view data often exhibit highly inconsistent missing patterns, posing significant challenges for incomplete multi-view cluster
arXiv:2604.18164v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliabi
arXiv:2601.03331v2 Announce Type: replace Abstract: Recent advances in Vision-Language Models (VLMs) have improved performance in multi-modal learning, raising the question of whether these models tru
arXiv:2604.16943v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual inf