Knowledge catalogue
Superb conversation between @bgreene and @GaryMarcus Very happy to get my confirmation bias pampered by mentions of interpolation vs extrapolation, and how having a better physics understanding might
arXiv:2602.06807v2 Announce Type: replace-cross Abstract: We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that av
arXiv:2605.18745v1 Announce Type: cross Abstract: Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve samp
arXiv:2603.01683v2 Announce Type: replace-cross Abstract: Injecting new reasoning knowledge into Large Language Models (LLMs) via post-training often induces catastrophic forgetting. Recent studies em
arXiv:2603.26720v2 Announce Type: replace-cross Abstract: Predicting surgical needle trajectories from endoscopic video is critical for robot-assisted suturing, enabling anticipatory planning, real-ti
arXiv:2505.17674v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. However, existing SNNs still exhibit a signif
arXiv:2511.04070v3 Announce Type: replace Abstract: As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users are often domain experts who expect not just answers
arXiv:2605.17929v1 Announce Type: new Abstract: Robotic in-hand manipulation requires reliable object-motion tracking under frequent visual occlusion, yet low-texture visuotactile images provide few s
arXiv:2605.17348v1 Announce Type: new Abstract: Recent advancements in LLM-based multi-agent systems have demonstrated remarkable collaborative capabilities across complex tasks. To improve overall ef
arXiv:2605.17320v1 Announce Type: cross Abstract: Computer-use agents increasingly operate inside live personal workspaces, where their actions can modify files, applications, GUI state, credentials,
arXiv:2605.18281v1 Announce Type: new Abstract: Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning probl
terrific deep dive on Mythos from @cloudflare Cloudflare's security team spent the last few weeks testing Anthropic's Mythos against fifty of our own repositories. What we learned about offensive AI,
arXiv:2603.01092v2 Announce Type: replace Abstract: Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. M
arXiv:2512.22471v5 Announce Type: replace-cross Abstract: Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analy
arXiv:2605.17480v1 Announce Type: new Abstract: Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates ne
arXiv:2605.18372v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in educational settings as interactive tools for collaboration. However, their tendency toward syco
arXiv:2605.16428v1 Announce Type: cross Abstract: Search engines traditionally complement online content platforms by directing users seeking information to external websites. The emergence of generat
arXiv:2602.07730v2 Announce Type: replace-cross Abstract: Across scientific disciplines, Laplacian eigenvectors serve as a fundamental basis for simplifying complex systems, from signal processing to
“the uncritical adoption of AI in science is alarming” Artificial intelligence is rapidly accelerating scientific output, but risks narrowing inquiry, weakening judgement and undermining how scientist
arXiv:2510.14466v3 Announce Type: replace-cross Abstract: Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and
arXiv:2605.17994v1 Announce Type: cross Abstract: New item growth is critical for maintaining a healthy ecosystem in large-scale e-commerce platforms. However, existing systems tend to prioritize pres
arXiv:2605.17772v1 Announce Type: new Abstract: Physical adversarial attacks often overfit single surrogate models and optimization objectives. While ensemble attacks can mitigate this, existing metho
arXiv:2605.16735v1 Announce Type: cross Abstract: The deployment of 5G Multicast-Broadcast Services (MBS) is emerging as a critical technology for spectral-efficient UHD content delivery and serving a
arXiv:2605.17788v1 Announce Type: cross Abstract: A fundamental challenge in recommender systems is balancing reliability for Low-Active Users (LAUs) with diversity for High-Active Users (HAUs). The k
arXiv:2605.18008v1 Announce Type: new Abstract: Uncertainty quantification (UQ) is critical for safety-critical domains like healthcare, yet it is rarely evaluated under realistic out-of-distribution
arXiv:2605.17575v1 Announce Type: cross Abstract: Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution s
arXiv:2605.18611v1 Announce Type: new Abstract: We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 huma
arXiv:2603.02667v2 Announce Type: replace Abstract: Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives d
arXiv:2602.19710v2 Announce Type: replace Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level percept
arXiv:2505.16831v3 Announce Type: replace-cross Abstract: Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like
arXiv:2602.22801v2 Announce Type: replace-cross Abstract: Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving
arXiv:2510.02590v2 Announce Type: replace Abstract: The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target net
arXiv:2605.16420v1 Announce Type: new Abstract: This paper addresses the problem of reconstructing missing or dropped frames in top-down drone video of autonomous surface vehicles performing structure
arXiv:2605.18192v1 Announce Type: new Abstract: Aerial-Ground Person Re-Identification (AGPReID) remains highly challenging due to drastic viewpoint variations between drones and fixed cameras. Existi
arXiv:2605.16393v1 Announce Type: cross Abstract: Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (Vi
arXiv:2605.17556v1 Announce Type: cross Abstract: Clay sculpting is a nuanced, artistic task involving dexterous manipulation with long-horizon planning to achieve high-level goals. As a robotics prob
arXiv:2603.18178v2 Announce Type: replace-cross Abstract: The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-co
arXiv:2605.16827v1 Announce Type: new Abstract: Participatory approaches to artificial intelligence are increasingly documented across public, civic, and humanitarian settings, but evidence about how
arXiv:2605.16775v1 Announce Type: cross Abstract: Self-supervised learning (SSL) has advanced medical image analysis be enabling learning form large unlabelled data. However, in brain magnetic resonan
arXiv:2605.17314v1 Announce Type: cross Abstract: We consider whether off-policy experience from a smaller, weaker model can elicit capability in a stronger learner that on-policy RL fine-tuning (e.g.
What we find most useful about CNA is that the intervention is simple yet powerful. The steering is a multiplicative ablation on a sparse set of MLP neurons, which makes CNA a clean addition on top of
arXiv:2605.17017v1 Announce Type: cross Abstract: Behavior Foundation Models (BFMs) enable scalable imitation learning (IL) by pretraining task-agnostic representations that can be rapidly adapted to
arXiv:2605.16362v1 Announce Type: cross Abstract: Activation steering offers a lightweight way to control LLMs without retraining, but its effectiveness varies sharply across concepts. Prior work ofte
arXiv:2605.16403v1 Announce Type: new Abstract: Despite rapid progress in video-capable MLLMs, we find that their apparent audio understanding in videos is often vision-driven: models rely on visual c
arXiv:2605.16600v1 Announce Type: cross Abstract: Cross-entropy pretraining and preference alignment update the same transformer weights, but leave geometrically distinct traces. We characterise this
arXiv:2605.18150v1 Announce Type: new Abstract: Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesi
arXiv:2601.16398v2 Announce Type: replace-cross Abstract: Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of
arXiv:2605.17173v1 Announce Type: cross Abstract: Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds
arXiv:2605.16547v1 Announce Type: new Abstract: Semantic communication has emerged as a promising paradigm for enabling goal-oriented networking. However, most existing semantic communication solution
arXiv:2512.07245v2 Announce Type: replace Abstract: Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language m
arXiv:2509.23183v3 Announce Type: replace Abstract: Test-time entropy minimization helps adapt a model to novel environments and incentivize its reasoning capability, unleashing the model's potential
arXiv:2511.23152v3 Announce Type: replace Abstract: Discovering discrete algebraic rules from data is a fundamental challenge in machine learning. We formalize this problem through Cayley-table comple
arXiv:2605.16250v1 Announce Type: cross Abstract: Distribution utilities are now expected to deliver bills that customers can actually read attach a defensible carbon number to every kWh sold and sche
arXiv:2510.15714v3 Announce Type: replace-cross Abstract: Second-order optimization methods offer superior convergence rates but are often bottlenecked by the wall-clock cost of Hessian computation an
a very procedural end. we will never know what the world might be like had OpenAI been forced to fully follow its original mission. Breaking News: A jury rejected Elon Musk’s lawsuit accusing OpenAI o
arXiv:2605.16017v1 Announce Type: new Abstract: In this paper, we present CT-AGD (Curvature-Tuned Accelerated Gradient Descent), an optimization method for non-convex optimization problems in deep lea
arXiv:2505.19241v2 Announce Type: replace-cross Abstract: The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various do
arXiv:2605.16054v1 Announce Type: cross Abstract: Recent work has framed decision-making as a sequence modeling problem using generative models such as diffusion models. Although promising, these appr
arXiv:2605.16015v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) for quadrotor flight control typically relies on Domain Randomization (DR) for sim-to-real transfer, resulting in ov
arXiv:2511.19115v2 Announce Type: replace Abstract: In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective,