All entries

My AI Engineer Singapore journey: Most exciting: First time traveling abroad after joining http://Z.ai, and my very first English talk on stage. Most challenging: Spoke in a three-speaker session alon

Clem Delangue reports that his follower count on X (formerly Twitter) is growing faster than on other social media platforms, and credits @nikitabier and their team for this success. The post suggests

arXiv:2605.15650v1 Announce Type: new Abstract: Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical ex

Omkar Godbole / CoinDesk: Nasdaq-listed Bitcoin Depot, North America's largest bitcoin ATM operator, files for bankruptcy, blaming “increasingly stringent compliance obligations” — Bitcoin Depot, the

arXiv:2605.16134v1 Announce Type: cross Abstract: Sharpness-aware minimization (SAM) encourages flat minima by perturbing parameters along directions of high loss curvature, but treats all parameter d

arXiv:2507.10236v2 Announce Type: replace Abstract: As generative Artificial Intelligence (AI) advances, the realism of AI generated imagery has reached a threshold capable of deceiving even vigilant

arXiv:2605.15559v1 Announce Type: new Abstract: Recent years have witnessed significant progress in autonomous navigation using reinforcement learning. However, existing approaches largely emphasize r

Nebius and @LangChain have partnered to integrate Nebius Token Factory with LangChain's Deep Agents. The integration, combined with LangChain's existing Tavily integration, gives teams building on Lan

arXiv:2605.15436v1 Announce Type: new Abstract: This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their

arXiv:2601.23030v2 Announce Type: replace-cross Abstract: Inference in nonlinear continuous stochastic processes on trees is challenging, particularly when observations are sparse and the topology is

arXiv:2605.15524v1 Announce Type: cross Abstract: Point cloud learning often rests on the premise that observed samples are noisy traces of an underlying geometric object, such as a manifold embedded

arXiv:2512.04745v3 Announce Type: replace-cross Abstract: The ability to flexibly compose previously acquired skills to execute intelligent behaviors is a hallmark of natural intelligence. Such compos

arXiv:2506.16129v2 Announce Type: replace Abstract: Neurosymbolic learning can use symbolic rules to provide supervision for latent concepts from weak labels, but it commonly assumes that the entities

arXiv:2605.15615v1 Announce Type: new Abstract: Efficient transfer learning of vision-language models (VLMs) commonly suffers from a Base-New Trade-off (BNT): improving performance on unseen (new) cla

NEW paper from Meta: Agentic Discovery of Neural Architectures. This is a hot new area of research! Keep an eye on it. NEW paper from Meta. (bookmark it) It's an agent system that autonomously discove

NEW paper worth reading. GPT-5.4 nano plus a critic-comparator orchestration loop hits 76.4% on SWE-bench Verified, matching standalone Gemini 3 Pro and Claude Opus 4.5 Thinking. The trick is to selec

Emily Forgash / Bloomberg: NextEra's 67B deal to buy Dominion, the largest utility merger in US history, signals a new era of utility consolidation to accommodate AI-driven power demand — NextEra Ener

arXiv:2605.15227v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) have attracted increasing attention as a means of accelerating scientific discovery; however, developing SDL software r

arXiv:2605.15470v1 Announce Type: new Abstract: Ocean dynamics are inherently chaotic, yet existing machine learning ocean models produce only deterministic forecasts. We introduce Njord, a probabilis

arXiv:2510.02307v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models often degrade when sampled at resolutions outside the final training resolution set. Prior work has largely emp

arXiv:2605.15828v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such a

Not all the good stuff at Build happens on the main stage. Join Microsoft for Startups on June 2 for Dev Your Own Way. Hands-on activations with @GitHub, @FireworksAI_HQ and @NVIDIAforStartups. Real c

Note that as of last summer Waymo said that LLMs/VLMs were experimental, and that their foundation model then could “process only a small amount of image frames, does not incorporate accurate 3D sensi

arXiv:2605.15219v1 Announce Type: new Abstract: Can AI systems discover genuinely new knowledge through iterative self improvement, and if so, at what cost? We introduce the NOVA framework, which mode

now i wanna see @drjimfan train robots in a sim doing this https://x.com/i/status/1795746905336725673 VIDEO: Competitors chase wheels of cheese down a steep hill, few remaining upright, in the annual

arXiv:2605.15726v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a scalable paradigm for improving the reasoning capabilities of large language mode

Agentic AI inference at one-tenth the cost per token with NVIDIA Vera Rubin NVL72. Agent sandboxes run 50% faster on NVIDIA Vera than traditional CPUs — while enterprise data queries are up to 3x fast

arXiv:2605.15603v1 Announce Type: cross Abstract: Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. Howe

arXiv:2605.16241v1 Announce Type: cross Abstract: Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inferen

arXiv:2605.15511v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have become the dominant framework for inductive graph-level learning. Yet most benchmarks focus on the regime n gg p, wher

arXiv:2605.15971v1 Announce Type: new Abstract: While reinforcement learning (RL) enables robots to acquire skills autonomously, its real-world deployment is severely limited by inefficient and unsafe

okay maybe it's a good time? We have a small colbert model trained at pplx, it is a continue-training of pplx-embed-0.6b, so native multilingual, just made it open and added a section how to use MaxSi

okay this is going kinda viral and tbh my original text was kind of messy, so here's a second pass with the help of Claude: -- Implement <SPEC>. As you work maintain a running implementation-notes.htm

arXiv:2602.10687v3 Announce Type: replace-cross Abstract: Existing forgery detection methods are often limited to uni-modal or bi-modal settings, failing to handle the interleaved text, images, and vi

arXiv:2605.15240v1 Announce Type: cross Abstract: This paper investigates the critical role of eigenalignments between the kernel matrix and learning targets in achieving robust generalization in lear

arXiv:2605.15860v1 Announce Type: new Abstract: Accurate geometric calibration of RGB-thermal infrared (TIR) stereo camera systems is essential for multimodal building envelope analysis, yet remains c

arXiv:2409.03897v3 Announce Type: replace Abstract: Large-scale multi-agent systems are often deployed across wide geographic areas, where agents interact with heterogeneous environments. There is an

arXiv:2605.15520v1 Announce Type: cross Abstract: Data attribution has become an important component of pricing, auditing, and governance in machine learning pipelines, yet most attribution methods im

arXiv:2605.15663v1 Announce Type: new Abstract: We study the minimax sample complexity of arepsilon-best arm identification in linear bandits. Given a compact action set X that spans R^d and an unknow

arXiv:2605.15435v1 Announce Type: new Abstract: Standard deep-learning pipelines usually choose the network architecture before training and keep it fixed throughout optimization. In contrast, a model

arXiv:2605.15309v1 Announce Type: new Abstract: Despite remarkable progress, image generation is far from solved. The dominant metric, FID, conflates sample fidelity with mode coverage and is close to

One thing to watch for with Claude & GPT is that the models expose too much irrelevant history in their outputs. Slides are given footers saying things like 'Better, more targeted version' if you aske

arXiv:2511.04484v2 Announce Type: replace-cross Abstract: We study the repeated optimal stopping problem, in which the same optimal stopping instance with an unknown distribution is solved repeatedly

arXiv:2602.03922v3 Announce Type: replace Abstract: Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context

arXiv:2605.15978v1 Announce Type: cross Abstract: Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, an

ComfyUI is recruiting for open positions, as announced on their social media. Interested candidates can view available job opportunities on their careers page at comfy.org/careers. This represents act