The Degeneracy Distillery
arXiv:2606.23838v1 Announce Type: new Abstract: When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish. Degeneracies render both label prediction and i
Knowledge catalogue
arXiv:2606.23838v1 Announce Type: new Abstract: When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish. Degeneracies render both label prediction and i
The Kimi API is now live on AWS Marketplace. 🚀 If your team is already running on AWS, you can now access Kimi with consolidated billing. Plus, eligible customers can apply Kimi API usage directly tow
This is the strongest ARC-AGI-2 performance to date by an open-source model. GLM-5.2 from @Zai_org on ARC-AGI (Verified) - ARC-AGI-2: 22.8%, 0.25 - ARC-AGI-1: 77.0%, 0.19 Performance is comparable wit
arXiv:2606.24336v1 Announce Type: new Abstract: Face Video Restoration (FVR) aims to recover high-fidelity facial videos from degraded input while preserving identity and semantic consistency across f
arXiv:2606.24596v1 Announce Type: new Abstract: As Large Language Models are increasingly deployed in critical applications, robustly evaluating their social biases is paramount. However, the current
arXiv:2606.24187v1 Announce Type: new Abstract: Long video understanding remains a daunting challenge for Multimodal Large Language Models (MLLMs) due to the excessive computation and memory footprint
arXiv:2606.24004v1 Announce Type: cross Abstract: Steering a large language model (LLM) toward a desired behavior typically relies on an iterative process of hand-crafting a prompt based on a careful
arXiv:2606.24331v1 Announce Type: new Abstract: Transformer-based language models have become the default substrate for natural language processing and the pace of new releases has made it hard for pr
arXiv:2606.24175v1 Announce Type: new Abstract: While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods
arXiv:2606.24256v1 Announce Type: new Abstract: Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a br
arXiv:2606.24302v1 Announce Type: new Abstract: Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on m
Try Kimi K2.7 and GLM 5.2 for free in Devin Desktop and CLI Kimi K2.7 Code and GLM 5.2 are available in Devin Desktop and CLI Both perform strongly on FrontierCode Extended, our benchmark for real-wor
arXiv:2507.01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing
arXiv:2606.24759v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) have shown strong potential for autonomous driving scene understanding, yet existing methods still fac
arXiv:2606.24282v1 Announce Type: new Abstract: High frame-rate RGB-D videos are crucial for a variety of downstream tasks, including motion analysis, dynamic scene understanding, and 3D reconstructio
Upbound Inc. today released Modelplane, a new open-source tool for managing artificial intelligence inference clusters. San Francisco-based Upbound is backed by $69 million from Alphabet Inc.’s GV fun
arXiv:2412.08147v2 Announce Type: replace-cross Abstract: Pareto fronts are useful to find good task-mixing strategies for multitask finetuning, but they are also costly to compute. To reduce costs, r
arXiv:2606.23759v1 Announce Type: cross Abstract: Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enable
arXiv:2606.24477v1 Announce Type: cross Abstract: Video large language models (LLMs) are often constrained by computation and memory budgets, leading them to use reduced frame rates and spatial resolu
arXiv:2606.24525v1 Announce Type: new Abstract: GUI agents powered by vision-language models show strong potential for automating digital tasks, yet frequently fail in long-horizon scenarios due to th
We benchmarked Mistral OCR against other frontier and open-weight models on ParseBench 📊 For a model at its price point, it is quite competitive! - It wins on semantic formatting - understanding strik
We built Claude for outbound sellers. AEs & SDRs can harness GTM engineering through chat across 40+ data sources, no technical skills required. We’ve had 57,548 queries in our first few weeks of beta
We have a new version of GPT-5.5 Instant for you, and it's much more fun to talk to. Our most-used model is now better at understanding the intent behind a question and adapting its response according
We open-source Qwen-AgentWorld-35B-A3B (MoE, 35B/3B active, 256K context) and AgentWorldBench. Two routes, one roadmap: 🔬 Build the simulator — scalable, controllable, surpassing real environments 🧠 I
We've provided some updated results on Mistral OCR that make use of the annotation feature for charts. The overall score is ahead of GPT-5.5 and just behind Gemini 3.1 Pro, which is quite impressive f
arXiv:2606.24344v1 Announce Type: cross Abstract: ODRL policy evaluators produce verdicts, but say nothing about the normative positions a policy brings into existence, the authority structures those
arXiv:2606.24370v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into decision-support roles in business and policy contexts. While prior benchmark studies have
arXiv:2606.23937v1 Announce Type: cross Abstract: Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test t
arXiv:2606.24119v1 Announce Type: cross Abstract: Discrete diffusion language model (DLM) fine-tuning inherits inexpensive diagnostics from denoising-time confidence monitors, but their PEFT-training
This post documents a Wordle game result where the player solved puzzle #1,830 in 3 attempts, with the final answer being a five-letter word where the 4th and 5th letters were guessed correctly in ear
arXiv:2606.24742v1 Announce Type: new Abstract: Generalist value models play a pivotal role in scaling robotic policy learning from large-scale, mixed-quality data. Mathematically, accurate value esti
arXiv:2606.24020v1 Announce Type: new Abstract: A modern model release reports scores on 40+ benchmarks and the same evaluations were run many more times before it: to track training progress, compare
arXiv:2606.24320v1 Announce Type: cross Abstract: We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0
arXiv:2606.22631v1 Announce Type: new Abstract: 4D dynamic scene understanding requires grounding language to a persistent worldline that binds identity, metric 3D motion, and synchronized multi-view
The conversations at last week’s AWS Summit NYC 2026 showed that AI evolution is entering a new phase. From physical robots tackling labor shortages to agentic systems reshaping enterprise operations,
A case study in why organizations should both incentivized their employees to explore AI uses that help them & have a Lab of dedicated AI builders Here, Cornell's finance & AI teams created a /treasur
arXiv:2606.20657v1 Announce Type: cross Abstract: Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to kee
arXiv:2606.21690v1 Announce Type: cross Abstract: Phishing is a multi-modal threat. We present a hybrid pipeline that scores each modality with its own engine and fuses the results. Three engines are
arXiv:2603.21911v2 Announce Type: replace Abstract: Synthetic hyperspectral image (HSI) generation is essential for large-scale simulation, algorithm development, and mission design, yet traditional r
arXiv:2511.03962v2 Announce Type: replace Abstract: Accurate intrinsic calibration is a crucial yet challenging prerequisite for 3D reconstruction using light field cameras. Existing calibration model
arXiv:2606.21511v1 Announce Type: cross Abstract: Respiratory rate is a vital indicator of pulmonary and cardiovascular health, yet conventional methods for estimating respiratory rate are often intru
arXiv:2606.21568v1 Announce Type: new Abstract: Student behavior detection is important for intelligent classroom analysis but remains challenging in large-class scenarios due to dense instance co-occ
arXiv:2606.21960v1 Announce Type: new Abstract: Laser-induced breakdown spectroscopy (LIBS) faces challenges in high-accuracy quantitative measurement under few-shot scenarios due to spectral noise an
arXiv:2606.21884v1 Announce Type: new Abstract: It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the
arXiv:2606.21244v1 Announce Type: new Abstract: 3D Gaussian Splatting achieves exceptional real-time rendering, but its substantial computational and storage demands hinder widespread deployment. Exis
arXiv:2603.20819v2 Announce Type: replace Abstract: This paper studies finite-sample set-membership identification for discrete-time bilinear systems under bounded symmetric log-concave disturbances.
arXiv:2602.14257v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains
arXiv:2606.22326v1 Announce Type: cross Abstract: Adam is one of the most widely implemented and influential modern optimizers. Why is it effective across different optimization problems in practice?
arXiv:2511.06675v2 Announce Type: replace-cross Abstract: Beside the standard stochastic gradient descent (SGD) method, the Adam optimizer due to Kingma & Ba (2014) is currently probably the best-know
arXiv:2606.20697v1 Announce Type: new Abstract: AlphaEarth Foundations (AEF) unify global remote sensing foundation embeddings through multimodal self-supervised learning, but their pretraining focuse
arXiv:2506.04018v3 Announce Type: replace-cross Abstract: As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents'
arXiv:2603.20179v3 Announce Type: replace-cross Abstract: Large language model-based AI agents are now able to autonomously execute substantial portions of a high energy physics (HEP) analysis pipelin
An agentic loop (compile, test, profile, revise) helps. Gemini 3 Pro went from 24 to 35/87 correct, then plateaued after ~20 steps. Feedback fixes syntax, not rank coordination, collective ordering, o
... and now you can buy your own! https://happy-pelicans.printify.me/product/29480311 Proceeds go to http://birdrescue.org, a local non-profit that rescues pelicans (among other birds) I printed a cus
David Gewirtz / ZDNET: Anthropic launches Claude Tag, an agentic AI coworker for Slack that can learn context, give suggestions, and more, in beta for Claude Team and Enterprise tiers — ZDNET's key ta
arXiv:2606.22054v1 Announce Type: cross Abstract: Detectors for GNSS radio-frequency impairments (jamming, spoofing, multipath) are usually reported with a single AUC measured on the distribution they
arXiv:2606.21470v1 Announce Type: cross Abstract: Vision--Language--Action (VLA) controllers are often built by extending vision--language models (VLMs) with action supervision, relying on multimodal
arXiv:2606.23147v1 Announce Type: new Abstract: We propose Assistron, a shared autonomy model that leverages Vision-Language-Action (VLA) models to assist the user in daily activities. Our approach is
arXiv:2606.21395v1 Announce Type: new Abstract: Atomistic structure and natural language have long been modeled separately, with language models either calling atomistic models as tools or being fine-
arXiv:2606.22966v1 Announce Type: new Abstract: Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent