Knowledge catalogue
arXiv:2608.11623v1 Announce Type: cross Abstract: Recent advances in Large Language Models (LLMs) have spurred cross-modal solutions for time-series forecasting. However, existing methods rely heavily
arXiv:2608.11227v1 Announce Type: new Abstract: Activation steering modifies a language model by adding a learned direction to its hidden activations, enabling targeted behavioral changes without retr
arXiv:2608.11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves durin
arXiv:2608.11480v1 Announce Type: cross Abstract: Hamilton-Jacobi (HJ) reachability provides a mathematically rigorous framework for safe control of dynamical systems, but its practical application is
arXiv:2608.12140v1 Announce Type: cross Abstract: Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing design
arXiv:2608.11493v1 Announce Type: new Abstract: Traditional offline recommendation evaluation relies heavily on complex, manually maintained feature pipelines that are difficult to scale. While Large
arXiv:2608.12025v1 Announce Type: cross Abstract: Medical devices are becoming more software-intensive, connected, and AI-enabled. Their development requires risk-management evidence aligned with ISO
arXiv:2608.11674v1 Announce Type: cross Abstract: On-policy rollout methods such as GRPO are central to post-training of large language models, yet they frequently suffer from training instabilities,
arXiv:2608.11396v1 Announce Type: cross Abstract: Extracting quantum information from a quantum state is a fundamental task of quantum computation, often requiring the estimation of many non-commuting
arXiv:2608.11537v1 Announce Type: cross Abstract: Generative semantic segmentation exposes structured predictions as images, but direct color decoding is susceptible to color drift and boundary mixing
arXiv:2512.11839v2 Announce Type: replace Abstract: Designing generalizable control policies that operate reliably under changing conditions is essential for robust network services in modern digital
arXiv:2608.11528v1 Announce Type: new Abstract: Group alignment adapts a language model to a demographic group to produce responses that reflect the group's opinions, values, and preferences. Sycophan
arXiv:2608.11787v1 Announce Type: cross Abstract: Generating actionable financial advice from business records demands that models integrate numerical reasoning, domain knowledge, and sound judgment,
Happy Thursday. On today's show: - @ibab (River AI) - @branninmcbee (CoreWeave) - @glangley (Flock Safety) - @sonyatweetybird (Sequoia) - @vytalow (Parasma) See you on the stream. SaaSpocalypse Revisi
arXiv:2608.11913v1 Announce Type: new Abstract: Video-to-audio (V2A) generation faces significant challenges in achieving precise temporal synchronization and high perceptual quality due to the comple
arXiv:2608.11980v1 Announce Type: cross Abstract: Semantic-ID generative recommenders represent each item as a short sequence of discrete semantic tokens and predict the next item by autoregressively
arXiv:2608.11451v1 Announce Type: cross Abstract: Modern end-to-end driving agents can achieve high average performance yet still violate basic traffic rules that a human driver would never miss. The
arXiv:2608.11660v1 Announce Type: cross Abstract: Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge
Gary Marcus posted on 13 Aug 2026 that, as a scientist, he is uncertain whether his conjectures about generative AI will be proven correct but remains confident that critics of the technology are pres
arXiv:2608.11766v1 Announce Type: cross Abstract: Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-leve
arXiv:2603.07499v3 Announce Type: replace-cross Abstract: Accurate estimation of the vehicle's sideslip angle and tire forces is essential for enhancing safety and handling performances in unknown dri
arXiv:2608.11354v1 Announce Type: new Abstract: Modern recommender systems treat observed actions as reliable proxies for user preferences, yet interactions often reflect exploration or comparison rat
arXiv:2608.11597v1 Announce Type: cross Abstract: As smart port infrastructures increasingly rely on autonomous maritime devices enabled by the Internet of Things (IoT), ensuring reliable onboard navi
arXiv:2608.11426v1 Announce Type: new Abstract: The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unk
arXiv:2608.11658v1 Announce Type: cross Abstract: Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deploymen
arXiv:2608.11753v1 Announce Type: new Abstract: Financial text is produced and interpreted within a market environment, yet financial text classifiers almost always receive text alone. We study whethe
arXiv:2608.11498v1 Announce Type: new Abstract: Natural-language-based scenario generation offers an intuitive means of describing rare and complex driving interactions, yet it is still uncertain whet
arXiv:2603.13891v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for automated text annotation in tasks ranging from academic research to content moderation
arXiv:2608.11919v1 Announce Type: new Abstract: Training large language models on limited hardware is increasingly a scheduling problem across GPU compute, host memory, PCIe transfer, and storage band
arXiv:2608.12198v1 Announce Type: cross Abstract: Recent research in machine and deep learning has shown the potential of learningbased motion planning approaches to improve the driving behavior of au
arXiv:2608.11681v1 Announce Type: cross Abstract: This work addresses the challenge of open-vocabulary instance segmentation (OVIS) and open-set panoptic segmentation (OSPS), which aim to recognize bo
arXiv:2608.11604v1 Announce Type: new Abstract: Large language model-based shopping agents are increasingly deployed in real-world e-commerce platforms, generating massive amounts of user interaction
arXiv:2608.12063v1 Announce Type: cross Abstract: Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely
arXiv:2608.11511v1 Announce Type: cross Abstract: In sequential decision making, an agent typically observes its environment and acts at every timestep. However, such active participation may not alwa
arXiv:2510.21112v3 Announce Type: replace-cross Abstract: High-definition 3D city maps enable city planning and change detection, which is essential for municipal compliance, map maintenance, and asse
arXiv:2608.11967v1 Announce Type: cross Abstract: Large language model agents increasingly rely on long-horizon reasoning to solve complex tasks involving planning, tool use, and memory. A critical ca
arXiv:2608.12190v1 Announce Type: cross Abstract: With the increasing complexity of cyber assaults in cloud environments, adaptable security solutions are needed that can support real-time detection a
arXiv:2608.11705v1 Announce Type: new Abstract: Aligned large language models (LLMs) are expected to exhibit safety behavior based on the content of the user request: they should refuse unsafe request
arXiv:2606.13840v2 Announce Type: replace-cross Abstract: Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and
arXiv:2608.12084v1 Announce Type: new Abstract: We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional (d=D) and bottleneck (d<D
arXiv:2507.22423v3 Announce Type: replace Abstract: To engineer AGI, we should first capture the essence of intelligence in a species-agnostic form that can be evaluated, while being sufficiently gene
arXiv:2608.12253v1 Announce Type: cross Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that
arXiv:2608.11368v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) spends most of its compute generating groups of long reasoning trajectories. Recent allocators red
arXiv:2608.11905v1 Announce Type: new Abstract: In many practical applications of generative AI systems, from tax rules to airline baggage allowance, responses to natural language queries must respect
arXiv:2608.11769v1 Announce Type: new Abstract: Vision-language-action (VLA) policies are expected to operate robustly across variations in the robot's initial configuration, yet aggregate task succes
arXiv:2603.06957v2 Announce Type: replace-cross Abstract: We study post-training linear autoregressive models with outcome and process rewards. Given a context oldsymbol{x}, the model must predict the
arXiv:2607.08837v2 Announce Type: replace-cross Abstract: Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject
arXiv:2503.01985v2 Announce Type: replace-cross Abstract: In the classic committee election setting each voter approves a subset of candidates and the goal is to select k winners based on these prefer
arXiv:2608.11830v1 Announce Type: cross Abstract: The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environme
arXiv:2608.12088v1 Announce Type: new Abstract: Generative models can produce images nearly indistinguishable from real data, yet rigorous and interpretable evaluation remains challenging. Conventiona
arXiv:2608.12306v1 Announce Type: cross Abstract: Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback:
arXiv:2608.11698v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods
arXiv:2608.11383v1 Announce Type: new Abstract: We study new algorithms for Contextual Bandits with Knapsack. In these problems, there are finitely many types of customers, products, and resources. Ea
I may have stumbled onto something interesting while trying to figure out a recurring artifact in ChatGPT image generation and editing (maybe applicable to other models as well?). It started with a ve
arXiv:2608.11587v1 Announce Type: cross Abstract: Recent advances in model design and self-supervised audio representations have improved speech and audio understanding, yet infant-centered naturalist
arXiv:2608.12232v1 Announce Type: new Abstract: Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, tempora
arXiv:2507.11773v2 Announce Type: replace-cross Abstract: The emergence of breakthrough artificial intelligence (AI) techniques has led to a renewed focus on how small data settings, i.e., settings wi
Wall Street Journal: Sources: Demis Hassabis pitched a new independent industry AI safety entity, modeled on the IAEA, to top Trump officials before stepping down as DeepMind's CEO — Demis Hassabis di
If you haven't checked the paper: https://arxiv.org/abs/2608.09867 TLDR: the authors show that you can swap out the 'encrypted' reasoning of the biggest model, like Opus, Sol, and put them into weaker
arXiv:2608.11951v1 Announce Type: cross Abstract: Extreme events in air transport, such as severe arrival delays and abnormal air times, cause cascading network disruptions with substantial operationa