Knowledge catalogue
Our evaluations show that frontier AI's cyber capabilities are advancing quickly. The length of cyber tasks frontier models can complete has been doubling every few months, and this rate has become fa
arXiv:2605.11525v1 Announce Type: new Abstract: Missing values are routinely treated as defects to be eliminated through deletion or imputation prior to machine learning. In many applied domains, howe
arXiv:2605.11178v1 Announce Type: new Abstract: Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians whose learned
arXiv:2512.05683v2 Announce Type: replace Abstract: Optical aberrations significantly degrade image quality in microscopy, particularly when imaging deeper into samples. These aberrations arise from d
arXiv:2605.11520v1 Announce Type: new Abstract: Unsupervised point cloud segmentation is critical for embodied artificial intelligence and autonomous driving, as it mitigates the prohibitive cost of d
arXiv:2512.11883v3 Announce Type: replace-cross Abstract: Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when 'anti-aesthetic' out
arXiv:2605.11511v1 Announce Type: cross Abstract: The validity of statistical inference depends critically on how data are collected. When data gathered through active data collection (ADC) are reused
arXiv:2605.11453v1 Announce Type: cross Abstract: Practitioners deploying multi-agent large language model (LLM) systems must currently choose between communication topologies such as chain, star, mes
arXiv:2605.12382v1 Announce Type: new Abstract: Large language models (LLMs) exhibit systematic preferences for well-known entities, a phenomenon often attributed to popularity bias. However, the exte
arXiv:2605.11535v1 Announce Type: new Abstract: Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are eithe
arXiv:2605.11299v1 Announce Type: cross Abstract: Code generation is typically trained in the primal space of programs: a model produces a candidate solution and receives sparse execution feedback, of
arXiv:2605.12289v1 Announce Type: new Abstract: Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general
arXiv:2509.06701v2 Announce Type: replace Abstract: We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with
probably correct, from @polynoamial: “with today’s AI models, intelligence is a function of inference compute.” but what about tomorrow’s models? never forget that humans are remarkably intelligent (t
arXiv:2605.12398v1 Announce Type: new Abstract: Estimating question difficulty is a critical component in evaluating and improving large language models (LLMs) for question answering (QA). Existing ap
arXiv:2605.11289v1 Announce Type: new Abstract: Average-reward reinforcement learning requires estimating the gain and the bias, which is defined only up to an additive constant. This makes direct dis
arXiv:2605.11697v1 Announce Type: new Abstract: This paper presents a kinematics-aware deep reinforcement learning framework based on Rainbow Deep Q-Networks (DQN) for cooperative peg-in-hole manipula
arXiv:2605.11151v1 Announce Type: cross Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key chall
arXiv:2605.11267v1 Announce Type: new Abstract: Accurate measurement of island area and coastline length is crucial for coastal zone monitoring and oceanographic analysis. However, traditional measure
arXiv:2605.11824v1 Announce Type: new Abstract: A realistic view of the vehicle's surroundings is generally offered by camera sensors, which is crucial for environmental perception. Affordable radar s
arXiv:2605.12046v1 Announce Type: cross Abstract: Quantum error correction (QEC) is essential for enabling quantum advantages, with decoding as a central algorithmic primitive. Owing to its importance
arXiv:2605.11284v1 Announce Type: cross Abstract: Background: External validation is essential for assessing the transportability of predictive models. However, its interpretation is often confounded
arXiv:2605.11564v1 Announce Type: new Abstract: Despite recent efforts to collect multi-task, multi-embodiment datasets, to design recipes for training Vision-Language-Action models (VLAs), and to sho
arXiv:2605.11469v1 Announce Type: new Abstract: Decentralized multi-agent path finding (MAPF) routes a team of agents on a shared grid, each acting from its own local view. The standard solution train
arXiv:2512.00775v2 Announce Type: replace Abstract: Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model
arXiv:2506.10664v2 Announce Type: replace-cross Abstract: Off-policy learning enables training policies from logged interaction data. Most prior work considers the batch setting, where a policy is lea
arXiv:2605.11114v1 Announce Type: new Abstract: Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside
arXiv:2605.12247v1 Announce Type: new Abstract: Contact-rich assembly is fundamental in robotics but poses significant challenges due to uncertainties in relative poses, such as misalignments and smal
arXiv:2605.11017v1 Announce Type: new Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and
arXiv:2603.15759v2 Announce Type: replace-cross Abstract: Robot learning requires adaptation methods that improve reliably from limited, mixed-quality interaction data. This is especially challenging
arXiv:2602.20150v2 Announce Type: replace-cross Abstract: Estimating simulation-ready scenes from real-world observations is crucial for downstream planning and policy learning tasks. Regretfully, exi
arXiv:2605.12039v1 Announce Type: new Abstract: Skill libraries enable large language model agents to reuse experience from past interactions, but most existing libraries store skills as isolated entr
arXiv:2602.22507v2 Announce Type: replace-cross Abstract: Residential floor plan generation requires not only geometric fidelity but also spatial configurational logic: shared living spaces should be
arXiv:2512.24768v3 Announce Type: replace-cross Abstract: We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitraril
arXiv:2603.07388v2 Announce Type: replace Abstract: Explaining out-of-distribution generalization has been a central problem in epistemology since Goodman's 'grue' puzzle in 1946. Today it's a central
arXiv:2503.23947v2 Announce Type: replace Abstract: Recent studies have shown that 2D convolution and self-attention exhibit distinct spectral behaviors, and optimizing their spectral properties can e
arXiv:2605.11134v1 Announce Type: new Abstract: Preference learning methods such as Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy an
arXiv:2605.11494v1 Announce Type: new Abstract: Distilled one-step (T=1) or few-step (Tleq4) diffusion models enable real-time image generation but often exhibit reduced sample diversity compared to t
arXiv:2605.10989v1 Announce Type: new Abstract: The training of Binary Neural Networks (BNNs) is fundamentally based on gradient approximation for non-differentiable binarization operations (e.g., sig
arXiv:2602.21625v2 Announce Type: replace Abstract: Vision-Based Tactile Sensors (VBTS) are essential for achieving dexterous robotic manipulation, yet the tactile sim-to-real gap remains a fundamenta
arXiv:2605.11538v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However
arXiv:2605.12064v1 Announce Type: new Abstract: Existing deep learning-based methods can capture shared features from optical and synthetic aperture radar (SAR) images for spatial alignment. However,
arXiv:2605.10991v1 Announce Type: new Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process
arXiv:2605.11205v1 Announce Type: new Abstract: Benchmark evaluation across AI and safety-critical domains overwhelmingly relies on simple averaging. We demonstrate that this practice produces substan
arXiv:2605.11361v1 Announce Type: new Abstract: Inference-time reward alignment asks how to turn a pre-trained diffusion model with base law p into a sampler that favors a reward r while remaining clo
arXiv:2605.10983v1 Announce Type: cross Abstract: Reinforcement learning (RL) has shown extraordinary potential in aligning diffusion models to downstream tasks, yet most of them still suffer from sig
arXiv:2605.12236v1 Announce Type: cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral clon
arXiv:2605.12288v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences o
arXiv:2511.10670v2 Announce Type: replace Abstract: Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing
arXiv:2605.11974v1 Announce Type: new Abstract: Large Language Models (LLMs) suffer from order bias, where their performance is affected by the arrangement order of input elements. This unfairness lim
arXiv:2605.05971v2 Announce Type: replace Abstract: Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly wit
arXiv:2506.01568v3 Announce Type: replace Abstract: Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained
arXiv:2605.12312v1 Announce Type: new Abstract: Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true prop
arXiv:2605.11020v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classica
arXiv:2605.12380v1 Announce Type: new Abstract: Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fr
arXiv:2510.03853v4 Announce Type: replace Abstract: We present UGround, a extbf{U}nified visual extbf{Ground}ing paradigm that dynamically selects intermediate layers across extbf{U}nrolled transforme
arXiv:2605.11491v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. How
arXiv:2605.11911v1 Announce Type: new Abstract: Predictive Coding (PC) is an influential account of cortical learning. Much of recent work has focused on comparing PC to Backpropagation (BP) to find w
arXiv:2505.19770v5 Announce Type: replace-cross Abstract: We present a fine-grained theoretical analysis of the performance gap between two-stage reinforcement learning from human feedback~(RLHF) and
arXiv:2605.12169v1 Announce Type: new Abstract: With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp