Knowledge catalogue
arXiv:2604.19544v1 Announce Type: new Abstract: Multimodal reward models (MRMs) play a crucial role in aligning Multimodal Large Language Models (MLLMs) with human preferences. Training a good MRM req
arXiv:2604.18603v1 Announce Type: cross Abstract: Bidirectional transformers are the foundation of many sequence modeling tasks across natural, biological, and chemical language domains, but they are
arXiv:2604.18829v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved impressive performance on visual perception and reasoning tasks with RGB imagery, yet they remain
Bloomberg: Dune Analytics: Polymarket's global trading volumes have fallen behind Kalshi in recent months; sources: product delays are contributing to Polymarket's decline — Polymarket, the long-time
arXiv:2604.18964v1 Announce Type: new Abstract: This paper introduces DW-Bench, a new benchmark that evaluates large language models (LLMs) on graph-topology reasoning over data warehouse schemas, exp
This post appears to be a humorous take on AI optimization and technology trends, likely referencing 'pixel-maxxing' (maximizing pixel-level performance or visual quality) in contrast to 'catfishing'
arXiv:2603.04445v2 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mod
Earlier this month, the inaugural Runway AI Summit brought together over 700 leaders across media, entertainment, gaming and advertising. The day was filled with firesides, panels and keynotes from le
arXiv:2603.12592v2 Announce Type: replace-cross Abstract: Routing algorithms for public transport, particularly the widely used RAPTOR and its variants, often face performance bottlenecks during the t
arXiv:2604.18639v1 Announce Type: cross Abstract: Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entro
arXiv:2510.09477v2 Announce Type: replace-cross Abstract: Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tab
arXiv:2604.18788v1 Announce Type: new Abstract: Apple Neural Engine (ANE) is a dedicated neural processing unit (NPU) present in every Apple Silicon chip. Mixture-of-Experts (MoE) LLMs improve inferen
arXiv:2604.18790v1 Announce Type: new Abstract: Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing m
Michael Acton / Financial Times: Efforts to revive chip manufacturing in Pennsylvania have been left in limbo by President Trump's sudden upending of US semiconductor policy over the past year — High-
arXiv:2604.19105v1 Announce Type: new Abstract: Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has
arXiv:2604.19564v1 Announce Type: cross Abstract: Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhib
arXiv:2604.17458v2 Announce Type: replace Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recen
🔥 Emad Mostaque on Doom Debates 🔥 @EMostaque helped kick off the modern AI revolution as the head of Stability AI, the company behind Stable Diffusion. But unlike most AI CEOs, he doesn't sugarcoat th
arXiv:2604.19547v1 Announce Type: new Abstract: Emotion-Cause Pair Extraction in Conversations (ECPEC) aims to identify the set of causal relations between emotion utterances and their triggering caus
We are officially moving past the era of one-size-fits-all AI. Enterprises today require highly specialized, role-specific tools to drive real productivity — but they cannot afford to sacrifice securi
arXiv:2510.23156v2 Announce Type: replace-cross Abstract: The growing demand for smart home interfaces has increased interest in non-intrusive sensing methods like vibration-based gesture recognition.
arXiv:2507.01918v3 Announce Type: replace-cross Abstract: We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform hi
arXiv:2509.03726v2 Announce Type: replace-cross Abstract: Sampling from unnormalized target distributions, e.g. Boltzmann distributions mu_{ext{target}}(x) propto exp(-E(x)/T), is fundamental to many
arXiv:2602.11631v2 Announce Type: replace-cross Abstract: Accurate and efficient wavefield modeling underpins seismic structure and source studies. Traditional methods comply with physical laws but ar
arXiv:2604.19559v1 Announce Type: new Abstract: Construction workers are highly vulnerable to heat stress, yet tools that translate real-time physiological data into actionable safety intelligence rem
arXiv:2604.19505v1 Announce Type: cross Abstract: Automatic keyword extraction from academic papers is a key area of interest in natural language processing and information retrieval. Although previou
Enjoyed the read? If you have deep experience in ML frameworks (training or inference) and love working on problems like these, our team is hiring! ML Systems Engineer, Frameworks & Tooling: https://j
arXiv:2510.18358v2 Announce Type: replace-cross Abstract: Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensemb
arXiv:2604.19652v1 Announce Type: cross Abstract: In this paper, we propose a deep-learning framework for environmental sound deepfake detection (ESDD) -- the task of identifying whether the sound sce
arXiv:2604.19699v1 Announce Type: new Abstract: The pursuit of truth is central to democratic deliberation and governance, yet political discourse reflects varying epistemic orientations, ranging from
arXiv:2504.01733v4 Announce Type: replace Abstract: This paper presents a class of epistemic logics that captures the dynamics of acquiring knowledge and descending into oblivion, while incorporating
arXiv:2411.16312v2 Announce Type: replace Abstract: Leveraging the overfitting property of deep neural networks (DNNs) is trending in video delivery systems to enhance video quality within bandwidth l
arXiv:2604.18916v1 Announce Type: new Abstract: In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be
arXiv:2512.20817v2 Announce Type: replace Abstract: Automated essay scoring (AES) has advanced significantly with neural language models, yet most systems remain opaque, offering little visibility int
arXiv:2604.18660v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work
arXiv:2604.19510v1 Announce Type: new Abstract: Variability in illumination is a primary factor limiting deep learning robustness for field-based plant disease detection. This study evaluates Histogra
arXiv:2604.19331v1 Announce Type: new Abstract: Understanding how policy is debated and justified in parliament is a fundamental aspect of the democratic process. However, the volume and complexity of
arXiv:2604.19526v1 Announce Type: cross Abstract: Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious
arXiv:2604.19341v1 Announce Type: cross Abstract: Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively
arXiv:2604.19054v1 Announce Type: new Abstract: The IEEE Low-Power Computer Vision Challenge (LPCVC) aims to promote the development of efficient vision models for edge devices, balancing accuracy wit
Every system that was regulated, either explicitly or implicitly, by the fact that they were effortful for humans (letters of recommendation, lawsuits, government filings, essays) will break. 🚨New pre
arXiv:2604.17406v2 Announce Type: replace Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is
arXiv:2604.19485v1 Announce Type: cross Abstract: Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimiza
Security intelligence and management solutions company Exabeam Inc. today announced new Exabeam Agent Behavior Analytics capabilities for agents built with Google Cloud’s Agent Development Kit and an
Cohere researchers Conway Zhu, Ali Edalati, and Zewen Shen published research on vLLM integration and quality recommendations. The blog post, shared via Cohere's official X account, likely discusses o
Excited to gather a group of technical builders Tuesday May 12 at @cognition's beautiful SF rooftop Join us for a Q&A with @ScottWu46 & Cognition employees on scaling up AI agents within F500 companie
Excited to share our work on production-ready W4A8 inference, now integrated in vLLM! By combining 4-bit weights (low memory) with 8-bit activations (high compute), we hit the sweet spot for both deco
Excited to share some big news: I've joined @FireworksAI_HQ President. I've spent my career at the intersection of great teams, disruptive technology, and massive market opportunity, from architecting
arXiv:2604.18786v1 Announce Type: cross Abstract: Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or ref
arXiv:2603.15956v2 Announce Type: replace-cross Abstract: Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (
arXiv:2604.19278v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misa
arXiv:2604.19034v1 Announce Type: new Abstract: Constructing structured spatial memory is essential for enabling long-horizon reasoning in complex embodied navigation tasks. Current memory constructio
arXiv:2604.19678v1 Announce Type: new Abstract: Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that
arXiv:2604.19702v1 Announce Type: new Abstract: Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and
arXiv:2601.12499v2 Announce Type: replace Abstract: Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which caus
arXiv:2604.19468v1 Announce Type: cross Abstract: Fairness audits of institutional risk models are critical for understanding how deployed machine learning pipelines allocate resources. Drawing on mul
arXiv:2604.19357v1 Announce Type: new Abstract: The evaluation of machine learning models typically relies mainly on performance metrics based on loss functions, which risk to overlook changes in perf
Fascinating how AI is getting better at diagrams like these (at least for ones that you could easily find on web search) but still making some pretty wacky errors — like confusing where the rear brake
arXiv:2604.18644v1 Announce Type: cross Abstract: Predictive policing systems that allocate patrol resources based solely on predicted crime risk can unintentionally amplify racial disparities through
arXiv:2512.05791v2 Announce Type: replace-cross Abstract: Purpose: The Unadjusted Langevin Algorithm (ULA) in combination with diffusion models can generate high quality MRI reconstructions with uncer