Knowledge catalogue
arXiv:2605.27428v1 Announce Type: new Abstract: Edge deployments of generative inference increasingly face two practical realities: per-device per-model performance is often unknown at deployment time
arXiv:2510.11170v2 Announce Type: replace-cross Abstract: With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computatio
arXiv:2605.27846v1 Announce Type: new Abstract: Large Reasoning Models are typically trained via reinforcement learning from verifiable rewards (RLVR). However, existing approaches adopt fixed weights
arXiv:2602.02150v2 Announce Type: replace-cross Abstract: Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels co
arXiv:2605.28272v1 Announce Type: new Abstract: Real-time synthesis of high-fidelity 3D character motion from audio is a pivotal component for next-generation interactive avatars and virtual assistant
Economy then vs now: GDP growth: 2024 2.8% 2026 1.6% Inflation: 2024 2.9% 2026 3.8% Wages: 2024 rising faster than inflation 2026 rising slower than inflation Unemployment rate: 2024 4% 2026 4.3% Jobs
arXiv:2605.28510v1 Announce Type: cross Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software development, yet they may reproduce training example
arXiv:2605.28409v1 Announce Type: new Abstract: Post-training using online reinforcement learning (RL) is an important training step for LLMs, including code-generating models. However, online RL for
arXiv:2605.28573v1 Announce Type: cross Abstract: The massive scaling of Large Language Models (LLMs) has made pretraining increasingly cost-prohibitive. While low-rank representation and orthonormal
arXiv:2605.27820v1 Announce Type: new Abstract: As AI agents increasingly operate in open, real-world environments, they require a deep synergy of multimodal perception, tool invocation with multi-hop
arXiv:2605.28401v1 Announce Type: new Abstract: Mixed Reality (MR) headsets promise a future of immersive telepresence where virtual humans blend indistinguishably into real or virtual surroundings. A
arXiv:2605.28101v1 Announce Type: cross Abstract: Predicting spatially varying Room Impulse Response (RIR) from sparse observations is a critical but highly challenging inverse problem for immersive s
arXiv:2605.28468v1 Announce Type: new Abstract: We present a hybrid robotic skin that combines electrical impedance tomography (EIT) with pneumatic tactile sensing to improve force reconstruction capa
arXiv:2605.27610v1 Announce Type: cross Abstract: The rapid growth of scientific publishing has made it increasingly difficult to track how fast-moving areas evolve. Search engines and LLM-based assis
Elon Musk explains the importance of Starlink and how it will increase GDPs of the countries “If you don’t have access to the internet, or it’s too expensive or low bandwidth, you cannot access MIT le
Elon Musk: If Kamala wins she'll hide the Epstein files, & be a threat to democracy. If Trump wins he'll release the Epstein files, & focus on the people. This idiot has NEVER been right about anythin
arXiv:2603.09882v2 Announce Type: replace-cross Abstract: Extrinsic dexterity leverages environmental contact to overcome the limitations of prehensile manipulation. However, achieving such dexterity
arXiv:2605.27482v1 Announce Type: cross Abstract: While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the bas
arXiv:2510.27266v2 Announce Type: replace Abstract: Autonomous graphical user interface (GUI) agents rely on accurate GUI grounding, which maps language instructions to on-screen coordinates, to execu
arXiv:2605.28016v1 Announce Type: new Abstract: Ultra-low-field (ULF) MRI offers portable and low-cost imaging but suffers from poor image quality. To address this, we present our submission to the 20
arXiv:2605.28630v1 Announce Type: new Abstract: Zero-Shot Anomaly Detection (ZSAD) aims to detect anomalies in unseen domains without target-domain adaptation. Recent CLIP-based methods have shown pro
arXiv:2605.28526v1 Announce Type: new Abstract: Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the
arXiv:2605.28264v1 Announce Type: new Abstract: Large Language Models (LLMs) often generate factually incorrect outputs, commonly termed hallucinations, that undermine trust and limit deployment in hi
arXiv:2605.27908v1 Announce Type: cross Abstract: Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited i
arXiv:2605.27741v1 Announce Type: new Abstract: Audio and omni-modal large language models exhibit impressive cross-modal reasoning capabilities. However, applying standard reinforcement learning post
arXiv:2505.17654v4 Announce Type: replace-cross Abstract: E-commerce platforms increasingly rely on Large Language Models (LLMs) and Vision Language Models (VLMs) to detect illicit or misleading produ
Evals shape agent behavior. Every eval is a vector that shifts the behavior of your agentic system. More evals ≠ better agents. Instead, build targeted evals that reflect desired behaviors in producti
This post combines learnings from LangChain’s work on evaluating deep agents and Anthropic’s guide to demystifying evals for AI agents into a practical guide. In this post, you will learn how to: 1) a
arXiv:2605.27618v1 Announce Type: new Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may
arXiv:2605.27950v1 Announce Type: new Abstract: Accurately assessing dietary behavior change receptivity is essential for designing effective just-in-time adaptive interventions (JITAIs) that promote
arXiv:2308.04823v5 Announce Type: replace Abstract: This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of la
arXiv:2605.28598v1 Announce Type: cross Abstract: LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has
arXiv:2512.15791v2 Announce Type: replace-cross Abstract: In Artificial Intelligence (AI), language models have gained significant importance due to the widespread adoption of systems capable of simul
arXiv:2603.08264v2 Announce Type: replace Abstract: Object pose tracking is a fundamental and essential task for robotics to perform tasks in the home and industrial settings. The most commonly used s
arXiv:2605.28312v1 Announce Type: cross Abstract: Event-based vision sensors offer asynchronous, high-temporal-resolution measurements that are attractive for low-latency robotic perception, but many
Every LLM API call depends on the inference engine underneath it. Tokenization, scheduling, prefill, decode, KV cache, batching, and streaming determine whether the experience is fast, scalable, and p
arXiv:2605.28270v1 Announce Type: new Abstract: Estimating the 9D pose of everyday objects from a single real-world image remains challenging. This is largely due to the lack of large-scale supervisio
Ethan Mollick critiques the widespread praise for Joseph E. Banks's predictions about AI's future, suggesting that the expectations placed on his foresight may be overstated. The post likely argues fo
arXiv:2605.27671v1 Announce Type: cross Abstract: Safety defenses for large language models (LLMs) are typically trained and evaluated on single-turn prompts, yet real attacks often unfold as indirect
Google created MapReduce more than 20 years ago to solve the scaling problems in data processing that the then young company was running into. The AI era that we are in now demands efficient, large-sc
arXiv:2605.27390v1 Announce Type: cross Abstract: Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck
arXiv:2605.28098v1 Announce Type: new Abstract: Multi-agent systems are increasingly deployed to support various tasks where agents interact to achieve individual and collective objectives. Although t
arXiv:2603.14515v2 Announce Type: replace Abstract: Neural-network wave functions in Variational Monte Carlo (VMC) have achieved great success in accurately representing both ground and excited states
arXiv:2511.14558v2 Announce Type: replace Abstract: We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used met
arXiv:2605.28215v1 Announce Type: new Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use th
arXiv:2603.22735v2 Announce Type: replace Abstract: Existing NLP work commonly treats contradictions as errors to be resolved by choosing which statements to accept or discard. Yet a key aspect of hum
arXiv:2605.27736v1 Announce Type: cross Abstract: Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing m
arXiv:2605.27929v1 Announce Type: cross Abstract: Active sensing links behavior and learning through an action-perception loop: actions determine the observations used to update internal predictive mo
arXiv:2605.28704v1 Announce Type: new Abstract: Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precis
arXiv:2509.26442v2 Announce Type: replace Abstract: The Robbins-Siegmund theorem establishes the convergence of stochastic processes that are almost supermartingales and is one of the most commonly us
arXiv:2605.28042v1 Announce Type: cross Abstract: Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but they do so as broad generalists largely trained for
arXiv:2605.28751v1 Announce Type: cross Abstract: Linear interpolation between fine-tuned checkpoints has been shown to trace the Pareto front between competing objectives, but whether extrapolative w
F Scott Fitzgerald, writing about someone who may as well have been Peter Thiel: “They were careless people, Tom and Daisy- they smashed up things and creatures and then retreated back into their mone
arXiv:2605.28389v1 Announce Type: new Abstract: While large language models have made significant progress in mathematical reasoning, they remain unreliable at judging the correctness of their own sol
arXiv:2604.04074v3 Announce Type: replace Abstract: LLM-based reviewing systems typically take only the manuscript as input, leaving literature and code-based claims hard to verify. We present FactRev
arXiv:2510.06970v2 Announce Type: replace-cross Abstract: Compliance with maritime traffic rules is essential for the safe operation of autonomous vessels, yet training reinforcement learning (RL) age
Fascinating results + Anthropic running away with it right now + So many people want to start their own company + Google over OpenAI + Vercel, Linear, Every, PostHog overperforming A great list if you
arXiv:2602.16284v2 Announce Type: replace Abstract: Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typi
arXiv:2605.27651v1 Announce Type: new Abstract: Autonomous space systems operating in extreme thermal environments require accurate and efficient thermal modeling to support both pre-mission system de
arXiv:2512.16483v2 Announce Type: replace Abstract: Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale pr