Knowledge catalogue
arXiv:2505.11809v3 Announce Type: replace Abstract: Visibility analysis in urban planning has traditionally relied on line-of-sight (LoS) simulations, which capture geometric occlusion. However, these
arXiv:2605.14912v1 Announce Type: new Abstract: Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or prop
arXiv:2605.14465v1 Announce Type: new Abstract: Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constra
arXiv:2605.15104v1 Announce Type: new Abstract: Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling benchmarks remain text-based. We study whether verified
arXiv:2602.14674v4 Announce Type: replace Abstract: Gradual argumentation is a field of symbolic AI which is attracting attention for its ability to support transparent and contestable AI systems. It
arXiv:2605.14445v1 Announce Type: new Abstract: Many real-world coding challenges are open-ended and admit no known optimal solution. Yet, recent progress in LLM coding has focused on well-defined tas
arXiv:2605.14920v1 Announce Type: new Abstract: Efficient UAV exploration in unknown environments requires rapid coverage expansion while maintaining accurate and reliable localization, since safe nav
arXiv:2605.14501v1 Announce Type: cross Abstract: This paper proposes a fully dynamic Deep Reinforcement Learning (DRL) method for rebalancing dockless bike-sharing systems, overcoming the limitations
Fun interview with Jacob Effron on the Unsupervised Learning podcast. It’s hard to imagine more of a dream Unsupervised Learning guest than @ylecun. Yann is one of the godfathers of AI, and he has som
arXiv:2410.06431v5 Announce Type: replace Abstract: Accurate uncertainty quantification in large language models (LLMs) is essential for reliable confidence estimation, yet fine-tuned LLMs often becom
Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated discussion about the reliability of AI systems in delegated workflows. We appreciate the interest in this work and want
arXiv:2605.14218v1 Announce Type: new Abstract: The key problem facing ChatGPT-like AI's use across society is that its behavior can shift, unnoticed, from desirable to undesirable -- encouraging self
arXiv:2605.15188v1 Announce Type: cross Abstract: AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently m
arXiv:2512.02482v2 Announce Type: replace Abstract: We propose G-SHARP, a commercially compatible, real-time surgical scene reconstruction framework designed for minimally invasive procedures that req
Gary Marcus critiques the claim that token prediction in large language models constitutes genuine thought or reasoning, using the analogy of smartphone autocomplete to illustrate that predictive text
arXiv:2605.13874v1 Announce Type: cross Abstract: Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they rep
The Gemini Live Agent Challenge is officially in the books! We challenged developers worldwide to break out of the traditional 'text box' paradigm by building next-generation AI agents. From our initi
Gemma-4-31B-it-Pearl supports 256K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to expand our Pearl powered
Gemma-4-31B-it-Pearl supports text and image input, 256K context, configurable thinking, function calling, and JSON mode. This is Together AI’s first Pearl-powered endpoint. Eventually, we plan to exp
arXiv:2605.14839v1 Announce Type: new Abstract: Traditional methods for classifying global navigation satellite system (GNSS) jamming signals typically involve post-processing raw or spectral data str
arXiv:2605.14215v1 Announce Type: new Abstract: Genetic circuit design remains a laborious, expert-driven process despite decades of progress in synthetic biology. We study this problem through code g
arXiv:2605.15018v1 Announce Type: cross Abstract: Shapley value and its priority-aware extensions are widely used for valuation in machine learning, but existing methods require pairwise priority to b
arXiv:2603.00772v2 Announce Type: replace-cross Abstract: Score-based generative models (SGMs) have achieved remarkable empirical success, motivating their application to a broad range of data distrib
arXiv:2605.14703v1 Announce Type: new Abstract: The high dynamic range (HDR) video ecosystem is approaching maturity, but the problem of upconverting legacy standard dynamic range (SDR) videos persist
arXiv:2510.25240v3 Announce Type: replace-cross Abstract: We present a general strategy for turning generative models into candidate solution samplers for batch Bayesian optimization (BO). The use of
arXiv:2605.14251v1 Announce Type: new Abstract: Conditional generative adversarial networks (cGANs) have enabled high-fidelity computational staining and destaining of hematoxylin and eosin (H&E) in d
arXiv:2605.14117v1 Announce Type: cross Abstract: An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between roo
arXiv:2509.14232v5 Announce Type: replace Abstract: Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style bench
arXiv:2602.10346v2 Announce Type: replace Abstract: Large language models (LLMs) must balance diversity and creativity against logical coherence in open-ended generation. Existing truncation-based sam
arXiv:2602.00992v2 Announce Type: replace Abstract: In many robot motion planning problems, task objectives and physical constraints induce non-Euclidean geometry on the configuration space, yet many
arXiv:2605.14406v1 Announce Type: cross Abstract: Large-scale pretraining on Earth observation imagery has yielded powerful representations of the natural and built environment. However, most existing
arXiv:2605.14475v1 Announce Type: new Abstract: Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes.
arXiv:2605.14809v1 Announce Type: new Abstract: Graph prompt tuning has shown great potential in graph learning by introducing trainable prompts to enhance the model performance in conventional single
arXiv:2602.06718v2 Announce Type: replace-cross Abstract: Citations provide the basis for trusting scientific claims; when they are invalid or fabricated, this trust collapses. With the advent of Larg
Go in with expectations that Grok Build is still beta, but improving almost every day Grok Build is amazing. The early beta just dropped for SuperGrok Heavy users and the first real feedback from deve
arXiv:2605.14237v1 Announce Type: new Abstract: Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (LLMs) offer unmatched flexibility in tool orchestra
Akshay Gangwar / Android Authority: Google confirms it's testing a new storage policy after some users reported that new Gmail accounts get only 5GB of free storage unless they add a phone number — Up
Google updated its spam policy to mark attempts to 'manipulate' its AI model in search results as spam, including results in AI Overview or AI Mode in Search, as Search Engine Land reports: 'In the co
arXiv:2605.14841v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) has become the dominant paradigm for parameter-efficient fine-tuning (PEFT) of large language models (LLMs). However, its b
arXiv:2603.07833v2 Announce Type: replace-cross Abstract: Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent's long-term outcomes. Most approaches in this par
arXiv:2605.14194v1 Announce Type: new Abstract: Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implic
arXiv:2603.21250v2 Announce Type: replace Abstract: Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former
arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routi
arXiv:2605.14968v1 Announce Type: new Abstract: GraphFlow is a visual workflow system designed to improve the reliability of agentic AI automation in multi-step, mission-critical processes. In these w
arXiv:2605.14790v1 Announce Type: cross Abstract: Research idea generation is the innovation-driving step of automated scientific research. Recently, large language models (LLMs) have shown potential
Great paper discussing agentic search vs. vector search. // Is Grep All You Need? // Pay attention to this on, AI devs. (bookmark it) They find that grep-style text search, when wrapped in the right a
GridCare Inc., a startup that helps data center operators more quickly connect their facilities to the electrical grid, has raised 64 million in funding. Early Nvidia Corp. backer Sutter Hill Ventures
Bianca Giacobone / Latitude Media: Gridcare, which uses AI to detect underused capacity in electric grids, raised a 64M Series A, following a 13.5M seed in 2025 — The grid intelligence startup uses AI
arXiv:2602.19533v2 Announce Type: replace-cross Abstract: This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed dur
arXiv:2605.14175v1 Announce Type: new Abstract: In long conversations, an LLM can produce a next utterance that sounds plausible but rests on premises the conversation has already abandoned. Context-m
arXiv:2605.14498v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly serve as personal assistants and workplace collaborators, where their utility depends on memory systems t
arXiv:2605.14317v1 Announce Type: new Abstract: Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. Howeve
arXiv:2605.14963v1 Announce Type: new Abstract: Stereo matching on top-bottom equirectangular images provides an effective framework for full-surround perception, as vertically aligned epipolar lines
Had the honor of sharing the stage with the one and only @sydneyrunkle at Interrupt 2026 to talk about Deep Agents. Sign-up for the Managed Deep Agents waitlist today to get early access! https://www.
Had the opportunity to catch up with @latentspacepod's recent episodes on a long road trip. Strongly recommend the one with @swyx x @jacobeffron. Today most thought pieces on where AI is heading that
arXiv:2605.15157v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich d
Anthropic has reset API rate limits for all users, specifically resetting both 5-hour and weekly rate limit quotas. This announcement suggests the company addressed rate limiting issues or provided us
arXiv:2605.14513v1 Announce Type: cross Abstract: Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the
arXiv:2605.14821v1 Announce Type: new Abstract: Face restoration under complex degradations still remains an ill-posed inverse problem due to severe information loss. Although diffusion models benefit
arXiv:2605.14487v1 Announce Type: cross Abstract: Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover