Knowledge catalogue
In a new interview with the Washington Post's @ben_guggenheim, ControlAI's US Director Connor Leahy explains why nobody really understands how AI works, the race to uncontrollable superintelligence, a
arXiv:2602.24007v3 Announce Type: replace-cross Abstract: Protein function relies on dynamic conformational ensembles, yet current generative models like AlphaFold3 often fail to produce ensembles tha
arXiv:2512.17504v2 Announce Type: replace-cross Abstract: Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) rema
arXiv:2606.29386v1 Announce Type: new Abstract: Predicting a patient's physiological trajectory under a planned treatment sequence is a prospective interventional problem, not standard time-series ext
arXiv:2606.29164v1 Announce Type: cross Abstract: Latent reasoning models perform multi-step inference directly in hidden-state space, yet the structure of these latent reasoning trajectories remains
Muon optimizer shows faster training speeds compared to traditional optimizers, but analysis reveals it sacrifices the simplicity bias that older optimizers maintain, potentially impacting model gener
arXiv:2606.30523v1 Announce Type: new Abstract: Covariance matrices serve as compact descriptors of feature distributions in many machine-learning pipelines, including domain adaptation and Gaussian e
arXiv:2606.29028v1 Announce Type: new Abstract: Keypose-based manipulation decomposes tasks into critical waypoints to simplify policy learning for long-horizon tasks, but existing approaches rely on
arXiv:2601.21864v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing metho
arXiv:2606.30243v1 Announce Type: new Abstract: This paper presents KYON, a hybrid wheel-legged quadruped robot equipped with a bimanual upper body for loco-manipulation tasks. The platform features a
arXiv:2606.29374v1 Announce Type: new Abstract: High-fidelity reconstruction of dynamic urban environments is a cornerstone of autonomous driving simulation and large-scale world modeling. While 3D Ga
arXiv:2606.30544v1 Announce Type: new Abstract: Latent Action Models (LAMs) learn action-like proxies from observation transitions. However, in multi-object or distractor-rich scenes, these visual eff
arXiv:2606.29938v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by hard prompts on which correct trajectories have low probability, so sampling mi
arXiv:2405.13947v2 Announce Type: replace Abstract: Deep neural networks based on reinforcement learning (RL) for solving combinatorial optimization (CO) problems are developing rapidly and have shown
arXiv:2606.29541v1 Announce Type: new Abstract: Role-semantic assignments provide priors over how heterogeneous agents may coordinate, but cooperative MARL systems instead settle on conventions throug
arXiv:2606.30537v1 Announce Type: cross Abstract: Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations.
arXiv:2606.29501v1 Announce Type: new Abstract: We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning. By pretraining a model to predict
arXiv:2606.30642v1 Announce Type: cross Abstract: Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts.
arXiv:2606.29113v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly mediate strategic interactions through natural language, making semantic control a critical element of commu
arXiv:2606.28827v1 Announce Type: new Abstract: End-to-end unmanned aerial vehicle (UAV) navigation can achieve impressive agility in simulation, yet its obstacle-avoidance behavior often degrades aft
arXiv:2410.05289v4 Announce Type: replace Abstract: Background: Neurosymbolic (NeSy) artificial intelligence describes the combination of logic or rule-based techniques with neural networks. Compared
arXiv:2606.29066v1 Announce Type: new Abstract: Masked diffusion language models (MDLMs) generate text by iteratively unmasking tokens, but their standard decoder reduces each step to a binary action:
arXiv:2606.28399v1 Announce Type: new Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual represe
arXiv:2606.29038v1 Announce Type: cross Abstract: Metric aggregation divergence (MAD) is the silent inconsistency that arises when distinct pipeline stages in an agent-based model coupled with a multi
Announcing: AI StopWatch In our last update, we mentioned we had something new in the works: a dedicated channel for news and analysis about AI. Subscribe to AI StopWatch An experiment from the writer
arXiv:2606.29462v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) inherit rich relational priors from their language backbones, yet often fail when asked to apply these relation
arXiv:2606.29265v1 Announce Type: new Abstract: Reasoning large language models (LLMs) have recently made much progress in complex problem-solving, leveraging internal reasoning (or thought) to guide
arXiv:2510.03142v2 Announce Type: replace-cross Abstract: Visual navigation policy is widely regarded as a promising direction, as it mimics humans by using egocentric visual observations for navigati
arXiv:2402.06359v2 Announce Type: replace Abstract: One of today's most pressing societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacti
arXiv:2606.30406v1 Announce Type: new Abstract: Modern large language models (LLMs) rely on reinforcement learning during post-training to push specific capabilities, yet integrating multiple capabili
arXiv:2606.29049v1 Announce Type: new Abstract: Knowledge Tracing (KT) is important for personalized education but traditionally suffers from two key limitations: a reliance on shallow ID-based repres
arXiv:2606.29760v1 Announce Type: new Abstract: Blind image quality assessment (BIQA) is commonly built on two basic learning paradigms: regression and ranking. Regression calibrates absolute scores,
arXiv:2606.30528v1 Announce Type: new Abstract: Current generative models, including GANs and diffusion models, have reached an outstanding level of photorealism, posing significant risks to privacy a
arXiv:2403.06728v2 Announce Type: replace Abstract: Radiology report generation (RRG) has attracted significant attention due to its potential to reduce the workload of radiologists. The performance o
arXiv:2506.08774v2 Announce Type: replace-cross Abstract: Different machine learning models can represent the same underlying concept in different ways. This variability is particularly valuable for i
arXiv:2606.28600v1 Announce Type: cross Abstract: Neuromorphic and edge computing research has focused on reducing the inference cost of neural network controllers, yet in physical closed-loop systems
arXiv:2606.30009v1 Announce Type: new Abstract: Graph anomaly detection (GAD) on text-attributed graphs (TAGs) is vital for applications such as fraud detection and academic integrity verification. Ex
arXiv:2606.18066v2 Announce Type: replace Abstract: We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving
arXiv:2601.22823v2 Announce Type: replace-cross Abstract: We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. I
arXiv:2603.16856v2 Announce Type: replace Abstract: The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the
arXiv:2606.29556v1 Announce Type: new Abstract: We propose Persona-Trained Monte Carlo (PTMC), a method for estimating distributions of market-outcome statistics by repeatedly simulating limit-order-b
arXiv:2606.30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported beh
arXiv:2606.29340v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a reasoning model on rollouts sampled from its own policy by matching a privileged teacher that also sees veri
arXiv:2606.28667v1 Announce Type: new Abstract: Sign languages are compositional systems where meaning arises by combining sublexical phonological parameters, such as handshape, location, and movement
arXiv:2606.28805v1 Announce Type: new Abstract: At competitive speeds and spins, a table tennis ball follows complex, counterintuitive trajectories that a robot must track and precisely counter within
arXiv:2603.23071v2 Announce Type: replace Abstract: Polarimetric imaging enables advanced vision applications such as normal estimation and de-reflection by capturing unique surface-material interacti
arXiv:2606.29908v1 Announce Type: cross Abstract: Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory syn
arXiv:2606.30068v1 Announce Type: new Abstract: Joint-embedding predictive (JEPA-style) objectives learn representations by predicting future latents. In doing so they can discard features that are ex
arXiv:2606.29092v1 Announce Type: cross Abstract: In a changing decision problem, standard dynamic-regret analyses have often equated the cost of non-stationarity to how far loss moves. However, it is
arXiv:2606.29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervis
arXiv:2606.30291v1 Announce Type: new Abstract: Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion meth
arXiv:2407.21359v2 Announce Type: replace-cross Abstract: Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental
arXiv:2606.29758v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) for Large Language Models increasingly relies on critic-free methods as a practical alternative to a
arXiv:2606.29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently trai
arXiv:2606.30362v1 Announce Type: cross Abstract: While current Behavior Foundation Models (BFMs) provide robust control priors for humanoids, they only execute pre-defined reference motions. As a res
arXiv:2606.30339v1 Announce Type: new Abstract: Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to
arXiv:2606.30518v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves language models by grounding generation in external context. However, it can be fragile when the retrieved
arXiv:2606.28939v1 Announce Type: new Abstract: Behavior-cloned diffusion policies are expressive but remain vulnerable to covariate shift: small deviations from demonstrated states can compound into
arXiv:2606.29577v1 Announce Type: cross Abstract: Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain f
arXiv:2603.05999v2 Announce Type: replace Abstract: Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360^irc images due to the substan