Knowledge catalogue
arXiv:2606.27228v1 Announce Type: new Abstract: Formal semantics has shown that sentence meanings arise by recursively composing lexical meanings, yet much of the literature on semantic universals mod
arXiv:2606.26753v1 Announce Type: new Abstract: Conversational memory retrieval optimizes relevance, yet a retrieved memory can be relevant and simultaneously outdated: a later turn updates, corrects,
arXiv:2606.26454v1 Announce Type: new Abstract: Sphere neural networks have achieved symbolic level syllogistic reasoning without training data, raising the question of where the limit of the scaling
arXiv:2606.26990v1 Announce Type: cross Abstract: Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration e
arXiv:2606.26687v1 Announce Type: new Abstract: In industrial environments, new product categories arrive sequentially, requiring continual anomaly detection without access to past data. Normalizing F
arXiv:2606.27153v1 Announce Type: cross Abstract: Matrix-orthogonalization-based optimizers, exemplified by Muon, have demonstrated strong convergence behavior across a wide range of modern deep learn
Dynamic workflows (generating harnesses on the fly) are a new form of test-time compute. But LLMs aren't great at building them. I often have to steer agents to generate complex patterns. Curious how
arXiv:2606.26337v1 Announce Type: new Abstract: Gradient Boosted Decision Trees (GBDT), exemplified by LightGBM, spend a dominant fraction of training time -- typically 65-70% -- constructing per-feat
arXiv:2606.27298v1 Announce Type: cross Abstract: We study the fundamental problem of learning a high-dimensional Gaussian truncated to an unknown halfspace. Lee, Mehrotra and Zampetakis (FOCS'24) rec
arXiv:2602.13720v2 Announce Type: replace Abstract: Autonomous aerial scanning of target structures is crucial for practical applications, requiring online adaptation to unknown obstacles during fligh
arXiv:2606.26192v1 Announce Type: new Abstract: Hash Learning (HL) is an efficient representation learning approach that maps real-valued data into compact binary representations. Traditional HL metho
arXiv:2606.27128v1 Announce Type: new Abstract: Wildfire monitoring from UAVs requires reliable reasoning over complex aerial scenes, where smoke, scale variation, and occlusions often limit RGB-only
arXiv:2606.26938v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have f
arXiv:2606.26515v1 Announce Type: new Abstract: Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating it
Fun fact: Dario once delayed the release of GPT-2 back at OpenAI, claiming it was too dangerous Dario fearmogged so hard that global AI progress got halted They could have quietly released it as Opus
arXiv:2606.26111v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has enabled users to synthesize music with text prompts, combining copyrighted lyrics, AI-composed melodies
arXiv:2606.26917v1 Announce Type: cross Abstract: Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or mi
GPT‑5.6 Sol launches with our most robust safety stack yet. We strengthened real-time protections against high-risk cyber activity and repeated misuse, then spent weeks hardening the system with human
This post highlights an apparent error where Google's Gemini AI attributed a film review to Roger Ebert for a 2016 movie, despite Ebert's death in 2013, making such a review impossible. The post, shar
Nous Research announced an upcoming HermesBench full leaderboard, indicating they are developing or expanding a benchmarking system, likely for evaluating their Hermes model family or related language
arXiv:2606.26164v1 Announce Type: new Abstract: Finding all modes of a multimodal black-box function is a fundamental challenge in optimization, Bayesian inference, and scientific computing. Existing
I feel like on X all you hear about is elaborate plans by firms to build their own AI stacks but in my experience companies are full of people who want access to Claude or ChatGPT and are pressuring t
arXiv:2606.26575v1 Announce Type: cross Abstract: Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based
If your benchmark relies on a static dataset or sampling from a static distribution densely known at training time, then it is fundamentally measuring memorization/retrieval. Which might be fine if yo
arXiv:2606.26356v1 Announce Type: new Abstract: Practitioners of prompt-composed agentic systems report a recurring failure mode: editing one prompt module silently shifts the behavior of others despi
arXiv:2606.26103v1 Announce Type: cross Abstract: Large Language Models (LLMs) have rapidly influenced many aspects of society, particularly education, due to their demonstrated ability to complete as
June Launches + Live Q&A Hear from Comfy's CEO @yoland_yan and product leaders Deep Mehta, Alexis Rolland, @jojodecayz , and Matt Miller who will walk you through what's new and answer questions live.
arXiv:2606.26179v1 Announce Type: cross Abstract: While WGS-based AMR prediction has reached high accuracy, existing models lack a mechanism to ground neural attributions in established biological pat
arXiv:2606.27334v1 Announce Type: new Abstract: Digital twins have emerged as a promising paradigm for personalized healthcare, enabling modeling of individual behavior and health trajectories. In cog
arXiv:2606.26315v1 Announce Type: new Abstract: Disturbance-robust UAV position control is easy to demonstrate in benign simulations but much harder to make fast in approach, well behaved near the tar
arXiv:2606.18195v2 Announce Type: replace Abstract: On-policy self-distillation (OPSD) has proven effective for post-training large language models (LLMs), yet its application to diffusion LLMs (dLLMs
arXiv:2602.08275v3 Announce Type: replace-cross Abstract: Elucidating the language-brain relationship requires bridging the methodological gap between the abstract theoretical frameworks of linguistic
This post discusses apparent contradictions in claims about Mythos' cybersecurity capabilities, suggesting tension between assertions that it excels at cyber defense versus reports that it failed to d
arXiv:2606.26795v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration dat
New paper on giving LLM agents experience that improves the weights and stays readable at the same time. Agent-experience methods split into two camps. Externalized natural-language rules stay interpr
Sam Altman suggests OpenAI is working toward offering more generous or unlimited token allowances for users, moving beyond current rate-limited pricing models. The post indicates this is an ongoing de
arXiv:2606.27154v1 Announce Type: new Abstract: Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. How
arXiv:2512.17621v2 Announce Type: replace Abstract: While Vision-Language Models (VLMs) have achieved notable progress in computational pathology (CPath), the gigapixel scale and spatial heterogeneity
arXiv:2512.02652v2 Announce Type: replace-cross Abstract: Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from
arXiv:2606.26549v1 Announce Type: new Abstract: Long-term time series forecasting (LTSF) plays a crucial role in fields such as energy management, finance, and traffic prediction. Transformer-based mo
arXiv:2606.26449v1 Announce Type: cross Abstract: Retrieval-augmented systems routinely present citations alongside generated answers, yet a citation does not confirm that the corresponding source mea
arXiv:2606.18786v2 Announce Type: replace Abstract: Robot soccer is a challenging testbed for multi-agent reinforcement learning because it combines partial observability, cooperative and adversarial
arXiv:2606.27369v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applica
arXiv:2606.26769v1 Announce Type: new Abstract: The adoption of powerful diffusion models is hindered by their significant inference latency. Recent ``cache-then-forecast'' schemes alleviate this issu
arXiv:2602.14486v2 Announce Type: replace-cross Abstract: The Platonic Representation Hypothesis suggests that representations from neural networks are converging to a common statistical model of real
arXiv:2606.26863v1 Announce Type: new Abstract: Rolling shutter (RS) cameras equip virtually all consumer devices, yet RS-aware relative pose estimation has remained impractical: the state-of-the-art
The Sakana Fugu Technical Report presents research on fugu (pufferfish), likely exploring novel approaches to AI model compression, efficiency, or optimization techniques, given Sakana AI's focus on e
arXiv:2603.30014v2 Announce Type: replace-cross Abstract: The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC),
arXiv:2603.10446v4 Announce Type: replace Abstract: Sign Language Production (SLP) faces a fundamental trade-off: direct text-to-pose models suffer from regression-to-the-mean effects, while dictionar
The Information: Sources: DeepSeek's $7.4B raise was prompted by the release of Mythos as CEO Liang Wenfeng realized DeepSeek couldn't compete without a massive war chest — Up until two months ago, De
arXiv:2606.26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet th
arXiv:2606.26800v1 Announce Type: new Abstract: Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly ch
arXiv:2606.27029v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) integrate physical priors into neural models by learning a system's Hamiltonian, improving generalization and sample
Taps sign We believe in broad access and plan to make GPT-5.6 Sol, Terra, and Luna generally available in the coming weeks. For now, at the request of the U.S. government, we’re starting with a limite
arXiv:2606.26874v1 Announce Type: new Abstract: Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous multimodal reasoning. However, adapting Multimodal Large Language Models (MLL
arXiv:2606.26511v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is
arXiv:2606.26634v1 Announce Type: new Abstract: Effective multi-task learning for surgical scene understanding is fundamentally hindered by annotation granularity mismatch; temporal workflow tasks suc
arXiv:2606.26963v1 Announce Type: new Abstract: Organizing knowledge from diverse text sources into interpretable hierarchies is crucial for tasks such as policy analysis, innovation monitoring, and e
NVIDIA has released GLM-5.2 NVFP4, a new quantization format for large language models. The announcement invites comparison with alternative quantization methods for performance and efficiency evaluat
arXiv:2606.26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains. However, their sear