Knowledge catalogue
i love the recent explosion of interactive data visualizations. more plz Who actually shapes AI policy in the U.S.? We mapped 1,812 entities: 745 people, 918 organizations, 2,925 relationships. Fronti
If you need proof of why AI output can't be trusted by default watch that page for more than 1 minute for any given LLM that produces output in there. An amazing time capsule of the unevenness of curr
arXiv:2605.00436v1 Announce Type: new Abstract: Concerns with the safety and reliability of applying large-language models (LLMs) in unpredictable real-world applications motivate this study, which ex
This newsletter entry discusses advancements in automating AI research and development processes, exploring how artificial intelligence systems are becoming capable of autonomously designing and impro
arXiv:2605.00664v1 Announce Type: new Abstract: We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework,
arXiv:2605.00324v1 Announce Type: cross Abstract: Large-scale ranking systems depend on thousands of features derived from user behavior across multiple time horizons. Typically requires model retrain
Anton Shilov / Tom's Hardware: Jensen Huang said Nvidia's market share of AI accelerators in China has “now dropped to zero” and that US export policy “has already largely backfired” — US export restr
arXiv:2408.11513v2 Announce Type: replace Abstract: This paper focuses on learning a Constrained Markov Decision Process (CMDP) via general parameterized policies. We propose a Primal-Dual based Regul
arXiv:2605.00642v1 Announce Type: cross Abstract: Graphical User Interface (GUI) grounding maps natural language instructions to the visual coordinates of target elements and serves as a core capabili
arXiv:2605.00718v1 Announce Type: new Abstract: Knee osteoarthritis (OA) assessment involves a natural but often underused label hierarchy: a coarse binary OA decision and a fine-grained Kellgren--Law
arXiv:2605.00702v1 Announce Type: new Abstract: Large language model (LLM) agents require long-term user memory for consistent personalization, but limited context windows hinder tracking evolving pre
arXiv:2605.00050v1 Announce Type: cross Abstract: Traffic accidents are routinely documented in textual reports, yet physically grounded accident reconstruction remains difficult because detailed scen
arXiv:2605.00416v1 Announce Type: new Abstract: Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. De
arXiv:2605.00556v1 Announce Type: cross Abstract: Partial driving automation creates a tension: drivers remain legally responsible for vehicle behaviour, yet their active control is significantly redu
arXiv:2605.00356v1 Announce Type: new Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every t
arXiv:2605.00762v1 Announce Type: new Abstract: We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-ba
arXiv:2605.00394v1 Announce Type: new Abstract: We present Mesh Field Theory (MeshFT) and its neural realization, MeshFT-Net: a structure-preserving framework for mesh-based continuum physics that cle
arXiv:2605.00393v1 Announce Type: new Abstract: Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms re
Diana Novak Jones / Reuters: New Mexico child safety trial: New Mexico asks a judge to declare Meta a public nuisance and to order it to pay $3.7B and overhaul its apps to protect children — The U.S.
NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T
arXiv:2605.00323v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) often suffer from hallucinations, generating descriptions that include visual details absent from the input image.
arXiv:2605.00432v1 Announce Type: new Abstract: Online Conformal Prediction (CP) struggles to balance temporal adaptability and structural stability. Feedback-driven methods (e.g., Adaptive Conformal
arXiv:2603.19397v2 Announce Type: replace Abstract: Non-pharmaceutical interventions (NPIs), such as diagnostic testing and quarantine, are crucial for controlling infectious disease outbreaks but are
arXiv:2605.00227v1 Announce Type: new Abstract: There are growing concerns about the risks posed by AI companion applications designed for emotional engagement. Existing safety evaluations often rely
arXiv:2510.26020v2 Announce Type: replace Abstract: Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls t
arXiv:2605.00345v1 Announce Type: new Abstract: Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rota
arXiv:2411.02327v4 Announce Type: replace Abstract: In the past year, video-based large language models (Video LLMs) have achieved impressive progress, particularly in their ability to process long vi
arXiv:2605.00384v1 Announce Type: new Abstract: Preference-based reinforcement learning offers a scalable alternative to manual reward engineering by learning reward structures from comparative feedba
arXiv:2605.00326v1 Announce Type: new Abstract: Single-prompt first-token probabilities from zero-shot vision-language model (VLM) safety classifiers are treated as decision scores, but we show they a
arXiv:2605.00099v1 Announce Type: cross Abstract: Despite rapid recent advances in quantum machine learning, the field is in many ways stuck. Existing approaches can exhibit serious limitations, and w
arXiv:2605.00623v1 Announce Type: new Abstract: This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar ene
arXiv:2407.16216v3 Announce Type: replace Abstract: Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle
arXiv:2604.07669v2 Announce Type: replace Abstract: Lead optimization in drug discovery requires improving therapeutic properties while ensuring that molecular modifications correspond to feasible syn
arXiv:2605.00654v1 Announce Type: new Abstract: For a risk-averse finite-horizon Markov Decision Problem, we introduce a special class of Markov coherent risk measures, called mini-batch measures. We
arXiv:2605.00468v1 Announce Type: new Abstract: Plain Language Summaries (PLS) aim to make research accessible to lay readers, but they are typically written in a one-size-fits-all style that ignores
arXiv:2605.00380v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diver
arXiv:2512.12744v3 Announce Type: replace Abstract: Activation sparsity offers a compelling route to accelerate large language model (LLM) inference by selectively suppressing hidden activations, yet
arXiv:2605.00528v1 Announce Type: cross Abstract: AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermedi
arXiv:2605.00787v1 Announce Type: new Abstract: While representation and similarity learning have improved the sample efficiency of Reinforcement Learning (RL), they are rarely used to shape policy up
arXiv:2605.00444v1 Announce Type: new Abstract: Multi-modal large language models (MLLMs) advance vision language understanding but face inherent limitations in long-video tasks due to bounded percept
arXiv:2605.00401v1 Announce Type: new Abstract: Recent EEG-to-image retrieval methods leverage pretrained vision encoders and foveation-inspired priors, but typically assume a fixed, center-focused vi
arXiv:2605.00449v1 Announce Type: cross Abstract: Learning-based MIMO detection has shown strong empirical performance, yet existing methods typically rely on fixed-depth architectures without explici
arXiv:2605.00069v1 Announce Type: new Abstract: Elastic distances like dynamic time warping (DTW) are central to time series machine learning because they compare sequences under local temporal misali
arXiv:2605.00553v1 Announce Type: new Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is an essential process for ensuring safety. Finding effec
arXiv:2503.10990v2 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying th
arXiv:2511.07756v4 Announce Type: replace Abstract: Diffusion models initialize generation from an isotropic Gaussian latent, yet changing only the random seed can substantially alter prompt faithfuln
arXiv:2605.00182v1 Announce Type: new Abstract: Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from
arXiv:2605.00365v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has achieved substantial gains in single-attempt accuracy (Pass@1) on reasoning tasks, yet often
arXiv:2605.00658v1 Announce Type: new Abstract: Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often tr
arXiv:2605.00364v1 Announce Type: new Abstract: Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existin
arXiv:2510.00072v2 Announce Type: replace Abstract: Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. W
arXiv:2605.00719v1 Announce Type: new Abstract: Unsupervised deraining has attracted attention for its ability to learn the real-world distribution of rain without paired supervision. However, the lac
arXiv:2506.11991v3 Announce Type: replace-cross Abstract: In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which
arXiv:2509.21723v4 Announce Type: replace Abstract: Achieving generalizable bimanual manipulation requires systems that can learn efficiently from minimal human input while adapting to real-world unce
VR founder Jaron Lanier says a future where people are paid for the data they give AI is better than one where everyone depends on billionaires to survive 'artificial intelligence is a marketing term,
arXiv:2605.00155v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has become a core post-training step for aligning large language models, yet the reward signal used
Way stronger. Today was huge for Musk, bad for OpenAI. The case against OpenAI is getting markedly stronger now that Musk is off the stand. Why? Musk’s lawyer is interrogating OpenAI founder Greg Broc
Well-known, well-respected AI expert Stuart Russell is now testifying at the Musk-OpenAI trial – despite OpenAI’s BS attempts to exclude him. Read the backstory here: A new filing just dropped in the
arXiv:2605.00018v1 Announce Type: new Abstract: Data-driven MoCap-to-radar models generate plausible micro-Doppler spectrograms, but do they actually learn the underlying physics? We introduce a physi
Why do these influencers always say “just published” for papers published last year? This paper is great, and I have written extensively about it in my newsletter. But c’mon. Apple didn’t “just publis