Knowledge catalogue
arXiv:2604.08707v1 Announce Type: new Abstract: Monadic second order logic (MSO2) plays an important role in parameterized complexity due to the Courcelle's theorem. This theorem states that the probl
ParseBench is here!📊 We’ve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale. It includes: • 2,000+ human-reviewed enterprise documents • 167,000 evaluatio
arXiv:2604.09415v1 Announce Type: cross Abstract: We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike exi
arXiv:2604.08987v1 Announce Type: new Abstract: As Large Language Models (LLMs) advance toward embodied AI agents operating in physical environments, a fundamental question emerges: can models trained
arXiv:2604.08991v1 Announce Type: cross Abstract: Small object-centric spatial understanding in indoor videos remains a significant challenge for multimodal large language models (MLLMs), despite its
arXiv:2604.08881v1 Announce Type: new Abstract: In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks: harmful ima
arXiv:2601.04884v2 Announce Type: replace Abstract: Executing a multi-agent plan can be challenging when an agent is delayed, because this typically creates conflicts with other agents. So, we need to
Google AI shared a post on X (formerly Twitter) directing followers to watch their content on YouTube, suggesting their video is also available on that platform for viewers who prefer that experience.
arXiv:2604.08598v1 Announce Type: cross Abstract: Text-based person search faces inherent limitations due to data scarcity, driven by stringent privacy constraints and the high cost of manual annotati
arXiv:2508.04853v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) has become a crucial tool for reducing the memory and compute costs of modern deep neural networks, including
arXiv:2604.08277v2 Announce Type: replace-cross Abstract: We present a quantum-inspired ARIMA methodology that integrates quantum-assisted lag discovery with fixed-configuration variational quantum ci
arXiv:2604.08703v1 Announce Type: cross Abstract: QoS-QoE translation is a fundamental problem in multimedia systems because it characterizes how measurable system and network conditions affect user-p
arXiv:2604.08570v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks
arXiv:2604.08976v1 Announce Type: new Abstract: We report that model quantisation restructures domain-level metacognitive efficiency in LLMs rather than degrading it uniformly. Evaluating Llama-3-8B-I
arXiv:2604.08810v1 Announce Type: new Abstract: Graph neural networks (GNNs) are increasingly applied to physical design tasks such as congestion prediction and wirelength estimation, yet progress is
arXiv:2511.19704v2 Announce Type: replace Abstract: Open-vocabulary semantic segmentation (OVSS) underpins many vision and robotics tasks that require generalizable semantic understanding. Existing ap
arXiv:2604.08739v1 Announce Type: cross Abstract: Ransomware poses a serious and fast-acting threat to critical systems, often encrypting files within seconds of execution. Research indicates that ran
ComfyUI is developing a realism character reference feature and is collecting user interest through a survey prior to its official launch. Users can sign up via the provided survey link to receive not
arXiv:2602.02188v2 Announce Type: replace Abstract: While large language models (LLMs) have shown strong performance in math and logic reasoning, their ability to handle combinatorial optimization (CO
arXiv:2602.11354v2 Announce Type: replace Abstract: The literature has witnessed an emerging interest in AI agents for automated assessment of scientific papers. Existing benchmarks focus primarily on
arXiv:2510.17640v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable performance on complex tasks through imitation learning in recent robotic man
arXiv:2604.08628v1 Announce Type: cross Abstract: Unauthorized disclosure of confidential documents demands robust, low-leakage classification. In real work environments, there is a lot of inflow and
arXiv:2509.20006v3 Announce Type: replace Abstract: With the large models easing the labor-intensive manipulation process, image manipulations in today's real scenarios often entail a complex manipula
arXiv:2604.08571v1 Announce Type: cross Abstract: While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their underlying reasoning processes remain highly ov
arXiv:2604.09452v1 Announce Type: cross Abstract: Safety guarantees are a prerequisite to the deployment of reinforcement learning (RL) agents in safety-critical tasks. Often, deployment environments
arXiv:2604.09285v1 Announce Type: new Abstract: The development of Large Language Models (LLMs) has catalyzed automation in customer service, yet benchmarking their performance remains challenging. Ex
Scaling model size is hitting diminishing returns. The real gains are in orchestration. Our Co-Founder & Co-CEO @yshoham makes the case in a rare long-form profile by @Calcalistech today. The man tryi
arXiv:2604.08988v1 Announce Type: new Abstract: Current LLM-based agents demonstrate strong performance in episodic task execution but remain constrained by static toolsets and episodic amnesia, faili
arXiv:2512.02231v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are expected to jointly interpret vision, audio, and language, yet existing video benchmarks rarely a
Ollama announced a meetup focused on Gemma, Google's open-weight language model family, scheduled for Wednesday. The event likely brought together developers and AI enthusiasts to explore running Gemm
arXiv:2604.09532v1 Announce Type: cross Abstract: Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual conten
arXiv:2604.09521v1 Announce Type: cross Abstract: When two agents of different computational capacities interact with the same environment, they need not compress a common semantic alphabet differentl
arXiv:2604.08819v1 Announce Type: cross Abstract: Content moderation systems classify images as safe or unsafe but lack spatial grounding and interpretability: they cannot explain what sensitive behav
arXiv:2604.08566v1 Announce Type: new Abstract: This study examines how different artificial intelligence architectures interpret sentiment in conflict-related media discourse, using the 2023 Gaza War
arXiv:2507.20185v2 Announce Type: replace Abstract: Session history is a common way of recording user interacting behaviors throughout a browsing activity with multiple products. For example, if an us
arXiv:2604.09037v1 Announce Type: cross Abstract: Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but over
arXiv:2511.23369v3 Announce Type: replace Abstract: Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-di
arXiv:2604.09025v1 Announce Type: cross Abstract: Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacit
arXiv:2604.08690v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretica
So the concern over Mythos and cybersecurity seems warranted. We conducted cyber evaluations of Claude Mythos Preview and found that it is the first model to complete an AISI cyber range end-to-end. 🧵
Natsuki Yamamoto / Nikkei Asia: Sources: SoftBank, Sony, Honda, and six other Japanese companies launch a new AI company to develop a 1T-parameter foundation model for “physical AI” by 2030 — TOKYO —
arXiv:2604.09212v1 Announce Type: new Abstract: Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preservin
arXiv:2604.08844v1 Announce Type: new Abstract: We study whether low-rank spectral summaries of LoRA weight deltas can identify which fine-tuning objective was applied to a language model, and whether
arXiv:2604.08625v1 Announce Type: cross Abstract: We develop a theoretical framework for generalization in the interpolating regime of statistical learning. The central question is why highly overpara
arXiv:2505.08518v2 Announce Type: replace-cross Abstract: The recovery of block-sparse signals with unknown structural patterns remains a fundamental challenge in structured sparse signal reconstructi
arXiv:2604.08597v1 Announce Type: cross Abstract: Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowle
arXiv:2604.09000v1 Announce Type: new Abstract: Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memo
arXiv:2511.08798v2 Announce Type: replace-cross Abstract: LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and
🚨 SUPER GEMMA 4 26B UNCENSORED IS INSANE LLM WIZARD COOKING AGAIN @songjunkr Dropped SuperGemma4-26B-Uncensored GGUF v2 and it’s trending on @huggingface🤗 This thing SMOKES the regular Gemma-4 26B: 🤯0
arXiv:2505.12318v2 Announce Type: replace Abstract: Federated Parameter-Efficient Fine-Tuning (Fed-PEFT) enables lightweight adaptation of large pre-trained models in federated learning settings by up
arXiv:2604.08948v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel in various general domains, they exhibit notable gaps in the highly specialized, knowledge-intensive, and legal
arXiv:2604.08563v1 Announce Type: cross Abstract: Extended reasoning models represent a transformative shift in Large Language Model (LLM) capabilities by enabling explicit test-time computation for c
arXiv:2604.08870v1 Announce Type: cross Abstract: Student dropout is a persistent concern in Learning Analytics, yet comparative studies frequently evaluate predictive models under heterogeneous proto
arXiv:2604.09047v1 Announce Type: new Abstract: Dental implant abutments serve as the geometric and biomechanical interface between the implant fixture and the prosthetic crown, yet their design relie
arXiv:2604.09388v1 Announce Type: cross Abstract: AI coding tools are widely adopted, but most teams plateau at prompt-and-review without a framework for systematic progression. This paper presents th
The @aiDotEngineer Europe conference last week was a blast! Fun fact: @swyx & team pre-computed Gemini Embedding 2 vectors for all speakers and sessions, and you can easily find similar sessions with
The entire team put a lot of effort into this benchmark. Document parsing and OCR certainly isn't solved, but now it is a bit easier to measure 🦙 We’re open sourcing the first document OCR benchmark f
The model is not the agent. The harness is. You need to read this recent study, and a blog post from @hwchase17 ... (links below). It will resonate deeply. This diagram from a recent paper captures so
arXiv:2604.09034v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) has significantly impacted the field of natural language processing, but their growing complexity ra
arXiv:2601.07220v3 Announce Type: replace Abstract: Multilingual language models (LMs) promise broader NLP access, yet current systems deliver uneven performance across the world's languages. This sur