All entries

Listen to the session or watch below AI companies want to build systems that understand the external world and overcome the limitations of LLMs. Recent developments have brought world models to the fo

.@RowanCheung anchored our Podcast Porch and interviewed @SundarPichai about what AI will look like in three years, his advice to young people experiencing the AI shift, our new Omni model and more. 🎤

This tweet by Hunt Lovell, shared by Harrison Chase, addresses questions about interpreters in the context of AI agent evaluation. It suggests that the effectiveness of interpreters should be validate

arXiv:2605.20868v1 Announce Type: new Abstract: KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empiric

Elon Musk posted a personal message expressing his enduring affection for two entities denoted as 'S & X,' likely referring to Tesla's Model S vehicle and X (formerly Twitter), the social media platfo

arXiv:2605.21138v1 Announce Type: new Abstract: Smoothed implicit contact dynamics enables gradient-based planning and control for contact-rich tasks without predefined mode sequences. However, safety

arXiv:2605.21186v1 Announce Type: new Abstract: Interpretability in object detection provides crucial confidence support for clinical auxiliary diagnosis. However, in tiny bacteria detection, traditio

arXiv:2605.20642v1 Announce Type: new Abstract: When annotators disagree, that disagreement can reflect epistemic uncertainty rather than simple label noise. We study hard-label delivery as an alterna

arXiv:2605.20545v1 Announce Type: cross Abstract: Transfer learning is an essential technique for many machine learning/AI models of complex structures such as large language models and generative AI.

arXiv:2605.20713v1 Announce Type: new Abstract: Multimodal IE in social media is difficult because a post may attach multiple images that are weakly related, redundant, or even misleading with respect

arXiv:2605.20395v1 Announce Type: new Abstract: A fundamental challenge in multi-robot motion planning is achieving sufficient coordination to avoid inter-robot conflicts without incurring the large c

arXiv:2605.20681v1 Announce Type: cross Abstract: Distributed principal component analysis (PCA) produces node-level estimates of both a mean vector and a principal subspace. Robustly aggregating thes

Storytelling is core to humanity’s DNA, stemming from our impulse to express ideals, warnings, hopes, and experiences. Technology has always been woven through the medium and the distribution: from ea

arXiv:2605.20396v1 Announce Type: new Abstract: Identifying latent variables and the causal structure involving them is essential across various scientific fields. While many existing works fall under

arXiv:2605.20712v1 Announce Type: new Abstract: Automatic speech recognition replaces typing only when correction costs less than manual entry, a threshold determined by error types, not counts: fixin

arXiv:2605.20308v1 Announce Type: new Abstract: Gradient-based attacks are important methods for evaluating model robustness. However, since the proposal of APGD, it has been difficult for such method

arXiv:2601.00418v2 Announce Type: replace-cross Abstract: We propose the Consensus-Based Privacy-Preserving Data Distribution (CPPDD) framework, a lightweight and post-setup autonomous protocol for se

arXiv:2605.20645v1 Announce Type: new Abstract: Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather

Seems GPT-5.2 reaches expert level in peer review: 45 scientists took 469 hours evaluating human & AI reviews on 82 papers. 'Surprisingly, current AI reviewers are competitive even with the top-rated

Self-Evolving in the Wild：Over the course of ~35 hours of continuous autonomous execution, the model performed 432 kernel evaluations across 1,158 tool calls. It wrote, compiled, profiled, and iterati

arXiv:2502.03752v5 Announce Type: replace Abstract: Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based ap

arXiv:2601.18577v2 Announce Type: replace Abstract: Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this usi

arXiv:2605.20602v1 Announce Type: new Abstract: Successive self-training on a language model's own outputs is widely characterized as a process of flattening: diversity drops, distributions narrow, an

arXiv:2605.21190v1 Announce Type: new Abstract: Despite the generative capabilities of diffusion and flow models, real-image editing remains constrained by a persistent trade-off between semantic edit

arXiv:2605.21341v1 Announce Type: cross Abstract: Functional bilevel methods estimate a lower-level function and plug it into a hypergradient, but this plug-in gradient can retain first-order bias whe

arXiv:2509.13648v3 Announce Type: replace Abstract: Generative recommendation plays a crucial role in personalized systems, predicting users' future interactions from their historical behavior sequenc

arXiv:2605.20510v1 Announce Type: new Abstract: Urban heat exposure is becoming an increasingly critical challenge due to the intensifying urban heat island effect. Fine-grained shade patterns, especi

arXiv:2605.20763v1 Announce Type: new Abstract: Rapid progress in aerodynamic shape optimization (ASO) has outpaced currently-available standardized evaluation frameworks. Fair comparison requires a u

Chloe Taylor / CNBC: Shares of quantum computing companies surged Thursday after the US government announced grants with equity stakes: D-Wave closed up 33%, Rigetti 30%, IBM 12% — Quantum computing s

arXiv:2602.06358v2 Announce Type: replace Abstract: We propose SHINE (Scalable Hyper In-context NEtwork), a scalable hypernetwork that can map diverse meaningful contexts into high-quality LoRA adapte

arXiv:2605.20191v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have recently attracted much attention for their ability to simulate human behavior and generate text that reflects

Many development teams are familiar with the hesitation that comes right before pushing a new feature live. As AI helps developers write code faster, the gap between rapid code generation and safe pro

arXiv:2504.19584v3 Announce Type: replace Abstract: Reconstructing dynamic radiance fields from video clips is challenging, especially when entertainment videos like TV shows are given. Many challenge

arXiv:2605.20998v1 Announce Type: new Abstract: Aspect-Term Sentiment Analysis (ATSA) in multi-aspect sentences faces a fundamental tradeoff between efficiency and expressiveness. Existing models eith

arXiv:2605.20733v1 Announce Type: new Abstract: Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and mainta

arXiv:2605.20450v1 Announce Type: new Abstract: Differentially private stochastic gradient descent (DP-SGD) enables private deep learning through per-example clipping and calibrated Gaussian noise, bu

arXiv:2605.20272v1 Announce Type: new Abstract: While humans readily generalize abstract concepts to more complex or larger tasks, building Reinforcement Learning (RL) systems with this ability remain

Finnish smart ring maker Oura Health Oy disclosed today that it has filed confidential paperwork with the U.S. Securities and Exchange Commission for an initial public offering. Share count and pricin

arXiv:2605.21135v1 Announce Type: new Abstract: As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness re

arXiv:2605.21147v1 Announce Type: cross Abstract: As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large langua

arXiv:2605.20850v1 Announce Type: new Abstract: Objective: Stage-wise workflows that separate model scaling and inverse kinematics can induce morphology-posture compensation, resulting in anatomically

So much for Nvidia’s cash flow. Wild. When does circular financing stop? Similar to a Ponzi Scheme, when cash outflows become greater than inflows. In this last quarter, NVDA cash grew by only ~600, a

Wired: Socket: TeamPCP, the gang claiming GitHub's repositories breach, also executed 20 “waves” of supply chain attacks recently, compromising 500+ pieces of software — GitHub is just the latest vict

arXiv:2605.20189v1 Announce Type: cross Abstract: Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with prima

arXiv:2605.05863v2 Announce Type: replace Abstract: Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computation

Rachel Metz / Bloomberg: Source: Cursor reached 3B in annualized revenue in late April and now has 3,000+ customers paying at least 100K each for its software on an annualized basis — Cursor's annuali