CIG: Exploration via Conditional Information Gain
arXiv:2605.20878v1 Announce Type: new Abstract: Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated
Knowledge catalogue
arXiv:2605.20878v1 Announce Type: new Abstract: Intrinsic rewards for exploration in reinforcement learning condition on different contexts: lifelong rewards score each transition against accumulated
arXiv:2605.20278v1 Announce Type: cross Abstract: Long-form image captioning exposes a reward granularity problem in RL: captions are judged as whole sequences, while the important errors occur at the
arXiv:2605.21352v1 Announce Type: new Abstract: The growing use of fast-switching power electronics has made partial discharge (PD) analysis under switching-voltage excitation increasingly important,
We’re over a year into the second Trump administration here in the US, and support for climate causes is weak. But climate tech companies are finding ways to survive and even thrive in this new enviro
arXiv:2605.20293v1 Announce Type: new Abstract: Predictive coding (PC) offers a local and biologically grounded alternative to backpropagation in the training of artificial neural networks, yet to dat
arXiv:2605.21372v1 Announce Type: new Abstract: Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world dri
arXiv:2512.19373v3 Announce Type: replace-cross Abstract: In developing data-driven modeling methodologies, there is an ongoing need to reconcile the strong predictive performance of opaque black-box
arXiv:2605.20796v1 Announce Type: new Abstract: We introduce a manifold-based framework for addressing optimization problems with equality and inequality constraints found in robotics. Our approach tr
arXiv:2605.20301v1 Announce Type: new Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making. However, object motion and ego-motion ofte
arXiv:2605.21143v1 Announce Type: cross Abstract: A soundscape is composed of three types of sound: biophony (sounds made by animals), geophony (natural abiotic sounds) and anthropophony (sounds made
arXiv:2605.20473v1 Announce Type: cross Abstract: Test-time scaling has emerged as a promising approach for improving code generation by exploring large solution spaces at inference time. However, exi
Cybersecurity startup Socket Inc. today disclosed that it has raised 60 million in funding at a 1 billion valuation. Thrive Capital led the Series C round with participation from Andreessen Horowitz,
arXiv:2605.20529v1 Announce Type: new Abstract: In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational b
Sense1 is announced as the first model capable of mapping olfactory activation patterns across multiple dimensions, establishing a standardized system for smell comparable to how RGB defines color and
Command A+ is available on @huggingface with W4A4 quantization 🤗 Cut your serving footprint dramatically with virtually zero performance degradation. Try it now: https://huggingface.co/CohereLabs/comm
arXiv:2605.21157v1 Announce Type: new Abstract: In modern warfare, drones are becoming an essential part of intelligence gathering and carrying out precise attacks in different kinds of hostile enviro
arXiv:2605.20971v1 Announce Type: new Abstract: The growing sophistication of GAN-based image manipulation presents significant challenges for digital forensics. This study compares the performance of
arXiv:2602.02304v2 Announce Type: replace-cross Abstract: Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning w
arXiv:2602.08686v2 Announce Type: replace Abstract: Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction. The retention decision is the
arXiv:2605.20555v1 Announce Type: new Abstract: We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Gr
arXiv:2605.21026v1 Announce Type: new Abstract: To accelerate automated remanufacturing, robotic disassembly must be considered during the product design phase. However, designers currently lack quant
arXiv:2605.20609v1 Announce Type: new Abstract: Compositional generalization is essential for reaching unseen goals under novel contextual variations in offline goal-conditioned reinforcement learning
arXiv:2407.08976v2 Announce Type: replace-cross Abstract: Recent years have seen a surge in methods for two-sample testing, among which the Maximum Mean Discrepancy (MMD) test has emerged as an effect
arXiv:2602.10455v2 Announce Type: replace-cross Abstract: Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behavior
arXiv:2605.20999v1 Announce Type: cross Abstract: We establish maximal concentration bounds for the iterates generated by stochastic approximation algorithms with general step sizes, where the noise h
arXiv:2605.20385v1 Announce Type: new Abstract: Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the
arXiv:2605.20834v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical e
arXiv:2605.21041v1 Announce Type: cross Abstract: Gaussian processes (GPs) offer a principled probabilistic model over functions, but exact inference is restricted to the linear-Gaussian regime. We es
Vercel introduced functionality to configure weighted traffic splits for Vercel Flags directly through the Vercel CLI, enabling developers to control what percentage of traffic sees different flag var
arXiv:2605.20566v1 Announce Type: new Abstract: Active perception in uncertain environments requires robots to navigate safely while acquiring informative observations to reduce map uncertainty. These
arXiv:2605.20758v1 Announce Type: cross Abstract: Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a contr
arXiv:2605.20270v1 Announce Type: new Abstract: A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on operator-local data, is installed in a regulated organi
arXiv:2605.06395v2 Announce Type: replace Abstract: Modern deep learning architectures increasingly contend with sophisticated signals that are natively infinite-dimensional, such as time series, prob
arXiv:2605.20357v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from a high-capacity teacher to a compact student by matching their predictive distributions, with tempe
arXiv:2605.20538v1 Announce Type: new Abstract: Evolving data streams induce joint nonstationarity in continual semantic segmentation, where semantic classes, input distributions, and supervision avai
arXiv:2605.20434v1 Announce Type: cross Abstract: We study the contradiction graphs associated with binary concept classes. For a class H subseteq {0,1}^X, the order-m contradiction graph G_m(H) has a
arXiv:2506.20764v2 Announce Type: replace-cross Abstract: Although there is a substantial body of literature on control and optimization problems for parabolic and hyperbolic systems, the specific pro
This post demonstrates using reference images with control maps in FLUX.2 instead of training LoRAs, allowing users to fuse a reference image with pose or edge control data while preserving identity a
arXiv:2503.15105v4 Announce Type: replace-cross Abstract: We study the fundamental computational problem of approximating optimal transport (OT) equations using neural differential equations (Neural O
Cool release from @p0. I think this use-case (agents paying content creators for access via @mpp) will be very big. Micropayment walls haven't worked (as Clay Shirky anticipated many years ago) becaus
arXiv:2605.20345v1 Announce Type: cross Abstract: Latent Gaussian models (LGMs) are a popular class of Bayesian hierarchical models that include Gaussian processes, as well as certain spatial models a
arXiv:2605.20756v1 Announce Type: new Abstract: Preconditioned optimizers are central to language model training, but their stochastic update rules are usually treated as direct approximations to popu
Qwen3.7-Max is an advanced AI model designed to function as a virtual coworker that enhances real-world productivity tasks. The model likely leverages Alibaba's Qwen technology to assist with work-rel
arXiv:2605.20247v1 Announce Type: cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mi
arXiv:2605.21317v1 Announce Type: new Abstract: The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive
arXiv:2603.20420v2 Announce Type: replace-cross Abstract: Nanopore sequencing can read substantially longer sequences of nucleic acid molecules, called reads, than other sequencing methods, which has
This post describes a user's experience building a local AI agent using Ollama, an open-source tool for running large language models locally. The article likely covers the practical implementation st
arXiv:2605.21049v1 Announce Type: new Abstract: Large language models (LLMs) reliably predict neural activity during language comprehension and transformer depth has been interpreted as mirroring hier
Logan Hitchcock / Decrypt: Crypto exchange Blockchain.com confidentially files for a US IPO; the UK-based company founded in 2011 was once valued at $14B — Long-running crypto exchange Blockchain.com
arXiv:2505.17354v3 Announce Type: replace Abstract: In many real-world settings--e.g., single-cell RNA sequencing, mobility sensing, and environmental monitoring--data are observed only as temporally
arXiv:2605.20771v1 Announce Type: new Abstract: Spurious correlations in real-world datasets cause machine learning models to rely on irrelevant patterns, undermining reliability, generalization, and
Cursor's new Composer 2.5 takes third on the Artificial Analysis Coding Agent Index and is ~10-60x lower cost than the higher-effort Opus 4.7 and GPT-5.5 variants above it. This release puts Composer
arXiv:2605.21001v1 Announce Type: new Abstract: Existing 3D clothed avatar reconstruction methods achieve high visual fidelity but ignore geometric structure and physical plausibility. They either mod
arXiv:2605.20680v1 Announce Type: new Abstract: Human Action Recognition (HAR) is a fundamental computer vision task with diverse real-world applications. Practical deployments often involve low-light
arXiv:2605.20936v1 Announce Type: cross Abstract: Hybrid attention architectures are becoming an increasingly important paradigm for improving LLM inference efficiency while preserving model quality,
arXiv:2605.21348v1 Announce Type: new Abstract: Solving partial differential equations with neural operators significantly reduces computational costs but remains bottlenecked by high training data re
arXiv:2605.20196v1 Announce Type: new Abstract: We investigate the hypothesis that real-data scaling laws are governed by progressive coverage of a latent predictive contribution spectrum rather than
We just announced the first release of Datasette Agent, a new extensible AI assistant for Datasette. I've been working on my LLM Python library for just over three years now, and Datasette Agent repre
Release: datasette-agent 0.1a3 'View SQL query' buttons for both visible tables and collapsed SQL result tool calls. Don't display empty reasoning chunks Improved handling of truncated responses - tab
datasette-agent-charts adds charts to Datasette Agent, powered by Observable Plot. The plugin extends Datasette Agent, which provides a conversational interface for asking questions about data in Data