Knowledge catalogue
arXiv:2604.23897v1 Announce Type: new Abstract: Markets are a promising way to coordinate AI agent activity for similar reasons to those used to justify markets more broadly. In order to effectively p
arXiv:2505.11334v4 Announce Type: replace Abstract: This work aims at a challenging task: human action-reaction synthesis, i.e., generating human reactions conditioned on the action sequence of anothe
Samantha Kelly / Bloomberg: Match Group invests 100M in Seattle-based Sniffies, a web-only platform for queer men with ~3M MAUs worldwide, paving the way for a possible acquisition — Match Group Inc.,
arXiv:2510.10486v2 Announce Type: replace-cross Abstract: Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks,
arXiv:2604.24461v1 Announce Type: cross Abstract: As human-AI cooperation becomes increasingly prevalent, reliable instruments for assessing the subjective quality of cooperative human-AI interaction
arXiv:2604.23235v1 Announce Type: new Abstract: Diffusion language models expose an explicit denoising trajectory, making it possible to ask when different kinds of information become measurable durin
arXiv:2604.23130v1 Announce Type: cross Abstract: Large language models (LLMs) can still be jailbroken into producing harmful outputs despite safety alignment. Existing attacks show this vulnerability
arXiv:2602.00981v2 Announce Type: replace-cross Abstract: Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical termi
arXiv:2604.24564v1 Announce Type: new Abstract: Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdat
arXiv:2504.09844v4 Announce Type: replace-cross Abstract: Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disj
arXiv:2604.24222v1 Announce Type: cross Abstract: Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal privat
arXiv:2604.24179v1 Announce Type: cross Abstract: Detecting hate speech in memes is challenging due to their multimodal nature and subtle, culturally grounded cues such as sarcasm and context. While r
A discussion about AI agents that can remember information from one interaction to the next, even across separate sessions , exploring how to implement persistent memory systems for personal AI assist
Mercury is the single “product” that has improved my life the most. I have always hated banks, invoicing platforms, and corporate cards. They make all of these things so incredibly easy. I haven’t had
arXiv:2510.17590v2 Announce Type: replace Abstract: We present MERIT, an inference-time modular framework for multimodal misinformation detection that decomposes verification into four specialized mod
arXiv:2511.14967v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Merma
arXiv:2604.22865v1 Announce Type: new Abstract: We introduce MeshLAM, a feed-forward framework for one-shot animatable mesh head reconstruction that generates high-fidelity, animatable 3D head avatars
arXiv:2604.24178v1 Announce Type: cross Abstract: Multi-Objective Alignment aims to align Large Language Models (LLMs) with diverse and often conflicting human values by optimizing multiple objectives
arXiv:2604.24625v1 Announce Type: cross Abstract: Unified multi-modal understanding/generative models have shown improved image editing performance by incorporating fine-grained understanding into the
arXiv:2604.24096v1 Announce Type: cross Abstract: Training reliable respiratory sound classification models remains challenging due to the limited size and subject diversity of datasets. Ensemble meth
Tuna-2 is a unified multimodal model that performs visual understanding and generation directly based on pixel embeddings, employing simple patch embedding layers to encode visual input without a VAE
arXiv:2604.22828v1 Announce Type: cross Abstract: Recent generative AI models have achieved remarkable breakthroughs in language and visual understanding. However, although these models can generate r
arXiv:2604.23289v1 Announce Type: cross Abstract: Due to the unprecedented success of deep learning, it has become an integral component in several multimedia computing applications in todays world. U
arXiv:2604.23539v1 Announce Type: new Abstract: The rapid proliferation of Generative AI necessitates rigorous documentation standards for transparency and governance. However, manual creation of Mode
arXiv:2604.23247v1 Announce Type: new Abstract: Avatar fingerprinting, i.e., verifying who drives a synthetic talking-head video rather than whether it is real, is a critical safeguard for authorized
Aditya Soni / Reuters: Microsoft is rolling out Copilot 365 to all of Accenture's roughly 743,000 employees, in the biggest enterprise deal for Copilot, following a 2023 pilot — Microsoft (MSFT.O) is
This post criticizes Microsoft's approach to integrating AI assistants into Outlook, expressing frustration that the AI chatbot has limited functionality and capabilities despite Microsoft's ownership
In this post, we explore what it takes to migrate a traditional text agent into a conversational voice assistant using Amazon Nova 2 Sonic. We compare text and voice agent requirements, highlight desi
arXiv:2604.24506v1 Announce Type: new Abstract: Biological function emerges from coupled constraints across sequence, structure, regulation, evolution, and cellular context, yet most foundation models
MiMo-V2.5-Pro is a fully open-sourced Mixture-of-Experts language model with 1.02T total parameters and 42B active parameters , available under the MIT License for commercial use, training, and fine-t
arXiv:2509.04802v3 Announce Type: replace Abstract: As large language models increasingly deployed into agentic systems, existing methods face critical gaps in observing, assessing, and mitigating dep
arXiv:2604.23129v1 Announce Type: cross Abstract: Knowledge workers face increasing challenges in synthesizing information from multiple documents into structured conceptual understanding. This proces
arXiv:2504.20018v2 Announce Type: replace-cross Abstract: Vector search plays a crucial role in many real-world applications. In addition to single-vector search, multi-vector search becomes important
arXiv:2604.24374v1 Announce Type: new Abstract: Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Repr
arXiv:2604.23788v1 Announce Type: new Abstract: Appreciating multi-figure paintings requires understanding how characters relate through subtle cues like gaze alignment, gesture, and spatial arrangeme
arXiv:2601.22246v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution
Mitchell Hashimoto: Mitchell Hashimoto, co-founder of HashiCorp, says his terminal application Ghostty will move off GitHub, citing GitHub's frequent outages — I'm GitHub user 1299, joined Feb 2008. —
arXiv:2604.24332v1 Announce Type: new Abstract: Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representatio
arXiv:2604.23108v1 Announce Type: cross Abstract: Large Language Models (LLMs) based on Mixture-of-Experts (MoE) are pivotal in industrial applications for their ability to scale performance efficient
arXiv:2508.05318v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for expanding the knowledge capacity of Multimodal Large Language Mo
arXiv:2604.23053v1 Announce Type: new Abstract: Mixed Binary Quadratic Programs (MBQPs) are an important and complex set of problems in combinatorial optimization. As solving large-scale combinatorial
arXiv:2506.01897v5 Announce Type: replace Abstract: With increasing size of large language models (LLMs), full-parameter fine-tuning imposes substantial memory demands. To alleviate this, we propose a
arXiv:2506.20332v4 Announce Type: replace Abstract: Vision-language model-based mobile agents have gained the ability to understand complex instructions and mobile screenshots, benefiting from reinfor
arXiv:2604.23107v1 Announce Type: cross Abstract: Causal effect estimation from observational data requires careful adjustment for confounding. Classical estimators such as inverse probability weighti
arXiv:2604.24280v1 Announce Type: new Abstract: We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment acti
Laguna XS 2 is a compact language model available through Ollama's model library, designed for efficient inference on resource-constrained devices. The model represents an update or variant in the Lag
Nemotron-3 is an open-source language model available through Ollama's model library, likely representing NVIDIA's Nemotron-3 family of instruction-tuned models designed for various NLP tasks. The mod
arXiv:2604.24472v1 Announce Type: cross Abstract: Multi-behavior recommendation aims to predict user conversions by modeling various interaction types that carry distinct intent signals. Recently, gen
arXiv:2604.23753v1 Announce Type: new Abstract: Multimodal affective computing analyzes user-generated social media content to predict emotional states. However, a critical gap remains in understandin
arXiv:2604.23272v1 Announce Type: new Abstract: Humans understand and interact with the real world by relying on diverse physical feedback beyond visual perception. Motivated by this, recent approache
arXiv:2604.24328v1 Announce Type: new Abstract: Monocular depth estimation (MDE) has witnessed remarkable progress driven by Convolutional Neural Networks and transformer-based architectures. However,
arXiv:2412.07160v3 Announce Type: replace Abstract: To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts
arXiv:2604.23264v1 Announce Type: new Abstract: Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich i
arXiv:2604.23620v1 Announce Type: new Abstract: We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coa
arXiv:2604.23530v1 Announce Type: cross Abstract: Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model inv
arXiv:2604.22881v1 Announce Type: cross Abstract: Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long
arXiv:2604.24158v1 Announce Type: new Abstract: Evaluating nuanced conversational travel recommendations is challenging when human annotations are costly and standard metrics ignore stakeholder-centri
arXiv:2604.23519v1 Announce Type: cross Abstract: Multi-plane architectures have become increasingly prevalent in the Fat-Tree networks of AI data centers. By leveraging multiple ports on a single net
arXiv:2604.23960v1 Announce Type: new Abstract: In this paper, we extend the recent Vector-Accelerated Motion Planning (VAMP) framework to multi-robot motion planning (MRMP). We develop two vector-acc
arXiv:2412.07157v3 Announce Type: replace Abstract: Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video under