Knowledge catalogue
arXiv:2605.21842v1 Announce Type: cross Abstract: Standard transformer attention computes pairwise similarity between queries and keys, treating all tokens as equally salient regardless of their intri
arXiv:2401.00139v3 Announce Type: replace-cross Abstract: This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reas
arXiv:2605.22607v1 Announce Type: new Abstract: Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation model
arXiv:2605.22185v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in general visual understanding. However, thei
arXiv:2605.22078v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficientl
arXiv:2605.21649v1 Announce Type: cross Abstract: Long-context decoding is increasingly limited by KV-cache memory traffic since each generated token attends over a cache whose size grows linearly wit
arXiv:2605.21970v1 Announce Type: cross Abstract: Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited
arXiv:2605.22391v1 Announce Type: cross Abstract: We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch on a multilingual recipe corpus. We aggregate 4.1
.@EricJorgenson on why Elon calls engineering magic: 'He's been thinking about these problems since he was in college. As a kid, he was very influenced by sci-fi and thinking about things that are pos
Essential context on OpenAI’s Erdos result I truly miss the age of science and transparency in AI. Especially given how much money and political power and governance and scientific understanding is at
arXiv:2503.17599v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated considerable potential in general practice. However, existing benchmarks and evaluation frameworks pr
arXiv:2605.22785v1 Announce Type: new Abstract: AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their p
arXiv:2605.20200v1 Announce Type: cross Abstract: This article presents a multimodal emotion recognition module integrated into a proactive Socially Interactive Agent (SIA) powered by generative artif
arXiv:2605.20630v1 Announce Type: new Abstract: Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure
arXiv:2605.22203v1 Announce Type: new Abstract: In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Aug
arXiv:2605.22186v1 Announce Type: new Abstract: Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking t
arXiv:2605.22139v1 Announce Type: new Abstract: Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensit
arXiv:2605.22208v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-driven image restoration agent demonstrates effectiveness in degradation coupling scenarios by flexibly selecting
arXiv:2605.21862v1 Announce Type: new Abstract: Chunked vision-language-action (VLA) policies predict multi-step robot controls, conditioning each update on the current visual observation alone. Yet r
arXiv:2605.21931v1 Announce Type: new Abstract: Recent Video Large Language Models (Video-LLMs) have demonstrated strong capabilities in video reasoning through reinforcement learning (RL). However, e
Excited to share our newly improved website for @xai. We overhauled every page to better showcase our various models and products, and help developers, enterprises and users get started quickly. Now l
arXiv:2605.22273v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VI
arXiv:2605.22072v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancing complex reasoning in large language models, and
Ryan Lawler / Axios: Farther Finance, which is building an AI-enabled wealth management platform for financial advisors, raised a 150M Series D at a 1B+ post-money valuation — Farther Finance, which i
arXiv:2605.22552v1 Announce Type: new Abstract: Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is
arXiv:2605.22422v1 Announce Type: new Abstract: Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. W
Brody Ford / Bloomberg: Filing: Zoom's stake in Anthropic is worth ~1.27B based on a February round which valued Anthropic at 380B; Zoom invested an additional 46M in recent months — Zoom Communicatio
Health Secretary Robert F. Kennedy Jr. removed the two leaders of the U.S. Preventive Services Task Force, which makes recommendations on preventive care such as mammograms and colonoscopies. Kennedy
arXiv:2605.21625v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus
arXiv:2605.22147v1 Announce Type: new Abstract: High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints a
arXiv:2605.21680v1 Announce Type: new Abstract: While autonomous multi-robots can achieve safe and coordinated navigation, they often struggle to adapt to unforeseen conditions and to capture operator
arXiv:2605.22057v1 Announce Type: new Abstract: Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarel
arXiv:2602.17186v2 Announce Type: replace Abstract: Large Vision Language Models (LVLMs) have achieved remarkable progress, yet they often suffer from language bias, producing answers without relying
arXiv:2605.21973v1 Announce Type: new Abstract: Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream,
arXiv:2605.22020v1 Announce Type: new Abstract: Feed-forward 3D Gaussian Splatting (3DGS) models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is funda
arXiv:2605.22018v1 Announce Type: new Abstract: The Flooded Road Environments Dataset (FRED) is, to our knowledge, the first multi-modal autonomous driving dataset specifically targeting the collectio
Dominic-Madori Davis / TechCrunch: Fresha, a London-based beauty and wellness booking marketplace, raised 80M from KKR's growth equity arm at a 1B+ valuation, bringing its total raised to 285M — Beaut
As enterprise software companies race to close the gap between product capability and market reach, the distribution scale — a company’s ability to move product through partner networks at volume and
arXiv:2605.22671v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior
arXiv:2605.20608v1 Announce Type: new Abstract: Realizing Level 4/5 Autonomous Networks (AN) demands a shift from static automation to agent-native intelligence. Current operations, reliant on rigid s
arXiv:2605.22649v1 Announce Type: new Abstract: Dual-energy X-ray absorptiometry (DXA) is widely used for large-scale skeletal assessment, yet learning controllable and interpretable factor-specific a
arXiv:2605.22462v1 Announce Type: new Abstract: We propose a five-stage methodology for causal feature analysis in transformer language models (probe design, feature extraction, causal validation, rob
arXiv:2605.21558v1 Announce Type: cross Abstract: Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts hav
arXiv:2605.22074v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard p
arXiv:2605.22413v1 Announce Type: new Abstract: Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multi
arXiv:2605.22003v1 Announce Type: new Abstract: Sentiment analysis, also referred to as opinion mining, primarily tries to extract opinion from any text-based data. In the context of movie reviews and
FTC to Require Cox Media Group, Two Other Firms to Pay Nearly $1 Million to Settle Charges They Deceived Customers About “Active Listening” AI-Powered Marketing Service Back in 2024 Cox Media Group we
Fuck off France is hardcore mode for founders: • Pay an employee 5K net → costs you 13K • Make profit → 30% corporate tax • Succeed → public calls you an exploiter • Get famous → kidnapping becomes a
Fuck this OpenAI employee, seriously fuck him. Also read this quantitative study, which I had nothing to do with, that says my technical predictions have bee largely correct. https://github.com/davego
arXiv:2605.22036v1 Announce Type: new Abstract: Despite significant progress in Vision-Language Navigation (VLN), existing approaches still rely on dense RGB videos that produce excessive patch tokens
arXiv:2605.22209v1 Announce Type: new Abstract: Video Capsule Endoscopy (VCE) poses a challenging multi-label temporal classification problem, requiring simultaneous localization of 8 anatomical regio
“Gary Marcus, former CEO of Geometric Intelligence and New York University professor, joins @SquawkStreet @CNBC to discuss why he still believes OpenAI could be the ‘WeWork’ of AI, why he finds Anthro
Gated DeltaNet-2 is almost exactly RWKV-7's DPLR recurrence, not acknowledging the elephant in the room 🙂 Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linea
arXiv:2605.22359v1 Announce Type: new Abstract: Eye tracking (ET) is a foundational technology for advanced AR/VR applications. However, training ET models for every new ET device is challenging: real
Gemini Flash 3.5 is such a disappointing model. It's intelligence and speed is awesome. Absolutely amazing. But it's been trained to max evals, not to be helpful to humans. It goes off and does random
arXiv:2507.23773v3 Announce Type: replace-cross Abstract: What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: sel
Unified AI service management lives or dies on context — and that context demands consolidating fragmented tools, data and operations into a single foundation. That consolidation imperative is now the
arXiv:2605.21605v1 Announce Type: new Abstract: Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal
arXiv:2605.22086v1 Announce Type: new Abstract: Human Activity Recognition (HAR) has shown remarkable effectiveness in various applications, such as smart healthcare and intelligent manufacturing. How
arXiv:2605.21849v1 Announce Type: cross Abstract: Mechanistic interpretability aims to explain a model's behavior by identifying causally responsible internal structures. Dictionary-based explainers s