Knowledge catalogue
arXiv:2604.19921v1 Announce Type: new Abstract: Negation is a common and important semantic feature in natural language, yet Large Language Models (LLMs) struggle when negation is involved in natural
arXiv:2506.19977v2 Announce Type: replace Abstract: Understanding which parts of the retrieved context contribute to a large language model's generated answer is essential for building interpretable a
Cool paper on diversity collapse in AI agents. It's a common issue with all the deployed multi-agent systems. New paper shows that multi-agent LLM systems converge on near-identical outputs over time,
arXiv:2604.20763v1 Announce Type: cross Abstract: Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristi
arXiv:2604.19926v1 Announce Type: new Abstract: Large language models can generate plausible game code, but turning this capability into iterative creative improvement remains difficult. In practice,
arXiv:2604.20389v1 Announce Type: cross Abstract: The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against
At Google Cloud, every day is Developer Day, but none so much as day 2 of Google Cloud Next, when we hold the developer keynote. This year’s topic? An in-depth look at Gemini Enterprise Agent Platform
arXiv:2604.20841v1 Announce Type: new Abstract: Recent advances in video generative models enable the synthesis of realistic human-object interaction videos across a wide range of scenarios and object
arXiv:2604.19765v1 Announce Type: cross Abstract: Recent work identifies a sparse set of 'hallucination neurons' (H-neurons), less than 0.1% of feed-forward network neurons, that reliably predict when
arXiv:2604.19859v1 Announce Type: cross Abstract: Edge-scale deep research agents based on small language models are attractive for real-world deployment due to their advantages in cost, latency, and
Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment
arXiv:2604.20577v1 Announce Type: cross Abstract: An assurance case is a structured argument document that justifies claims about a system's requirements or properties, which are supported by evidence
arXiv:2602.09781v2 Announce Type: replace-cross Abstract: This study investigates the explainability of generative diffusion models in the context of medical imaging, focusing on Magnetic resonance im
arXiv:2604.19754v1 Announce Type: new Abstract: Automated scoring of students' scientific explanations offers the potential for immediate, accurate feedback, yet class imbalance in rubric categories p
arXiv:2604.20760v1 Announce Type: new Abstract: Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for vid
arXiv:2604.20429v1 Announce Type: new Abstract: Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and com
arXiv:2510.25223v3 Announce Type: replace Abstract: Event log data, recording fine-grained user actions and system events, represent one of the most valuable assets for modern digital services. Howeve
arXiv:2604.19837v1 Announce Type: new Abstract: Autonomous agents operating in open-world tasks -- where the completion boundary is not given in advance -- face denominator blindness: they systematica
arXiv:2509.20138v2 Announce Type: replace Abstract: Minimax-based search algorithms with alpha-beta pruning and transposition tables are a central component of classical game-playing engines and remai
arXiv:2604.19789v1 Announce Type: new Abstract: We present an autonomous large language model (LLM) agent for end-to-end, data-driven materials theory development. The model can choose an equation for
arXiv:2604.20055v1 Announce Type: new Abstract: Hospital Quality Improvement (QI) plays a critical role in optimizing healthcare delivery by translating high-level hospital goals into actionable solut
arXiv:2603.09283v2 Announce Type: replace Abstract: Removing objects from videos remains difficult in the presence of real-world imperfections such as shadows, abrupt motion, and defective masks. Exis
arXiv:2604.20006v1 Announce Type: new Abstract: Personalized agents that interact with users over long periods must maintain persistent memory across sessions and update it as circumstances change. Ho
arXiv:2604.20191v1 Announce Type: cross Abstract: Interpretable driver attention prediction is crucial for human-like autonomous driving. However, existing datasets provide only scene-level global gaz
GPT-5.5 achieved state-of-the-art performance on the ARC-AGI-2 benchmark, with scores ranging from 85.0% on maximum difficulty tasks to 33% on low difficulty tasks. The model demonstrated consistent i
arXiv:2604.20382v1 Announce Type: new Abstract: Rising demand for mental health support has increased interest in using Large Language Models (LLMs) for counseling. However, adapting LLMs to this high
arXiv:2604.19794v1 Announce Type: new Abstract: Rough set theory models uncertainty by approximating target concepts through lower and upper sets induced by indiscernibility, or more generally, by gra
arXiv:2503.08321v2 Announce Type: replace Abstract: Vision graph neural networks have emerged as a popular approach for modeling the global and spatial context for image recognition. However, a signif
A 7B agent that beats GPT-4o. Lossless weight compression that speeds up inference by 177%. An arena where 23 teams battled across 103,000 adversarial rounds. This year at ICLR, Lambda is presenting t
arXiv:2604.19844v1 Announce Type: cross Abstract: Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and
arXiv:2604.20136v1 Announce Type: cross Abstract: Correcting errors in long-video understanding is disproportionately costly: existing multimodal pipelines produce opaque, end-to-end outputs that expo
arXiv:2604.19834v1 Announce Type: new Abstract: Functional fitness movements are widely used in training, competition, and health-oriented exercise programs, yet consistently enforcing repetition (rep
Kimi K2.6 achieved the top ranking on MathArena, a benchmark for evaluating mathematical problem-solving capabilities in open-source language models. This announcement highlights the model's superior
arXiv:2502.12911v3 Announce Type: replace Abstract: Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL ge
arXiv:2601.14896v2 Announce Type: replace Abstract: Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multiling
arXiv:2604.19815v1 Announce Type: new Abstract: Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically pl
arXiv:2604.20226v1 Announce Type: new Abstract: Speech-preserving facial expression manipulation (SPFEM) aims to modify facial emotions while meticulously maintaining the mouth animation associated wi
arXiv:2604.20796v1 Announce Type: new Abstract: We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a nativel
arXiv:2604.19787v1 Announce Type: cross Abstract: Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these
arXiv:2603.04950v2 Announce Type: replace-cross Abstract: Differential medical VQA models compare multiple images to identify clinically meaningful changes and rely on vision encoders to capture fine-
arXiv:2604.20317v1 Announce Type: new Abstract: GAN-based facial attribute editing is widely used in virtual avatars and social media but often suffers from attribute entanglement, where modifying one
arXiv:2604.20361v1 Announce Type: new Abstract: Object Referring-guided Scanpath Prediction (ORSP) aims to predict the human attention scanpath when they search for a specific target object in a visua
One change over the last six months is that in every big company I talk, at least a few senior people absolutely get AI — they experiment (a lot of OpenClaw, surprisingly) & they have an intuitive sen
OpenResearcher is an open-source AI agent designed to conduct long-horizon deep research tasks, enabling autonomous investigation and analysis across extended research workflows. The project is mainta
arXiv:2603.21373v2 Announce Type: replace-cross Abstract: In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Amon
arXiv:2604.20834v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency a
arXiv:2604.19773v1 Announce Type: cross Abstract: The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large langu
arXiv:2604.20146v1 Announce Type: cross Abstract: Grounded Multimodal Named Entity Recognition (GMNER) aims to extract named entities and localize their visual regions within image-text pairs, serving
arXiv:2512.08923v2 Announce Type: replace Abstract: We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in mul
arXiv:2604.19768v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit systematic miscalibration with rhetorical intensity not proportionate to epistemic grounding. This study tests th
arXiv:2604.19888v1 Announce Type: new Abstract: Driver gaze estimation is essential for understanding the driver's situational awareness of surrounding traffic. Existing gaze estimation models use dri
arXiv:2604.19791v1 Announce Type: new Abstract: Attitude change - the process by which individuals revise their evaluative stances - has been explained by a set of influential but competing verbal the
arXiv:2604.20158v1 Announce Type: new Abstract: Enterprise deployment of long-horizon decision agents in regulated domains (underwriting, claims adjudication, tax examination) is dominated by retrieva
arXiv:2505.07849v2 Announce Type: replace-cross Abstract: Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language
Thanks to @lmsysorg ！ Try it on SGLang now!🚀🚀 🚀 Qwen3.6-27B is here, and we have day 0 support on SGLang ✅ 27B params, beats Qwen3.5-397B-A17B across major coding benchmarks → Agentic coding → Text +
ChatGPT Images 2.0 generates highly realistic images that are difficult to distinguish from authentic photographs, raising concerns about misinformation and deepfakes. The new model features improved
arXiv:2507.21166v2 Announce Type: replace-cross Abstract: Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic dr
arXiv:2604.01577v2 Announce Type: replace-cross Abstract: We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizat
Three shifts in the AI stack today: - OpenAI ships GPT-5.5 as a mid-cycle drop before its IPO - Hugging Face's ML Intern beats Claude Code and Codex on research - Pliny used Claude Opus 4.7 to jailbre
arXiv:2604.20117v1 Announce Type: new Abstract: Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language