Knowledge catalogue
arXiv:2605.04752v1 Announce Type: new Abstract: Accurate traffic congestion classification requires models that jointly capture roadway scene context and non-stationary traffic motion, yet most prior
I really enjoyed chatting with @mattturck, was a great discussion. Deeply thoughtful conversation with @zicokolter, board member at @OpenAI and head of the machine learning department at @CarnegieMell
If point #4 is true, things are gonna get really wild. Hot take on Elon’s surprise decision to rent 30 megawatts of compute to Anthropic: 1. It’s a tacit concession that xAI is not all that close to A
I'm really excited about this as a new tool in our interpretability tool kit In a new paper, we present NLAs, an unsupervised method for converting an LLM's internal state into human-readable text. I'
arXiv:2407.14861v3 Announce Type: replace-cross Abstract: With the growing access to administrative health databases, retrospective studies have become crucial evidence for medical treatments. Yet, no
arXiv:2605.04064v1 Announce Type: cross Abstract: Reasoning capabilities are crucial for reliable medical visual question answering (VQA); however, existing datasets rarely include reasoning explanati
arXiv:2605.04355v1 Announce Type: new Abstract: Autonomous driving systems rely heavily on robust sensor fusion to perceive complex envi- ronments. Traditional setups using RGB cameras and LiDAR often
OpenAI introduced a 'Trusted Contact' feature in ChatGPT that allows users to designate emergency contacts who can request access to their account in case of incapacity or death. This feature provides
arXiv:2605.04063v1 Announce Type: new Abstract: Alzheimer's Dementia (AD) is a progressive neurodegenerative disease marked by irreversible decline, making reliable modeling of its progression essenti
This post discusses the dynamics of artificial superintelligence (ASI) development as a competitive race, arguing that competitive pressures make it difficult to slow progress until a critical inflect
arXiv:2605.04425v1 Announce Type: new Abstract: Vision-language models such as CLIP achieve strong visual-textual alignment, but often suffer from overfitting and limited interpretability when adapted
This post appears to be a satirical commentary on social media sensationalism, using the absurd claim that Earth's revolution around the sun is 'breaking news' to critique how trivial or well-establis
arXiv:2605.04769v1 Announce Type: new Abstract: Heterogeneous Face Recognition (HFR) aims at matching face images captured across different sensing modalities, such as thermal-to-visible or near-infra
arXiv:2605.05110v1 Announce Type: new Abstract: Designing reward functions for agile robotic maneuvers in reinforcement learning remains difficult, and demonstration-based approaches often require ref
arXiv:2505.00753v5 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-bas
arXiv:2605.04295v1 Announce Type: new Abstract: LLMs' overconfidence, particularly when hallucinating, poses a significant challenge for the deployment of the models in safety-critical settings and ma
arXiv:2605.05071v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) frequencies promise multi-gigabit connectivity for vehicle-to-everything (V2X) networks, but face challenges in terms of seve
Many, many OpenAI employees quit over safety concerns, including @DKokotajlo, William Saunders, @sjgadler, etc as well @Janleike. The founders of Anthropic such as @DarioAmodei and @jackclarkSF may ha
Gary Marcus criticizes the credibility and practices of X (formerly Twitter) influencer accounts, likely highlighting misleading claims, engagement manipulation, or questionable expertise common among
arXiv:2605.03847v1 Announce Type: new Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates
arXiv:2605.04180v1 Announce Type: new Abstract: Large Language Models exhibit strong reasoning and semantic understanding capabilities but often hallucinate in domains that require expert knowledge, a
arXiv:2605.03216v1 Announce Type: cross Abstract: Strategy-proofness is a fundamental desideratum in mechanism design, ensuring truthful reporting and robust participation. Stability is another centra
Sam Tobin / Reuters: Meta challenges Ofcom in UK High Court over the Online Safety Act, which calculates levies based on global, not UK, revenue, in a case scheduled for October — Facebook and Instagr
arXiv:2605.05003v1 Announce Type: new Abstract: Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluat
arXiv:2605.04680v1 Announce Type: new Abstract: EEG-based visual neural decoding aims to align neural responses with visual stimuli for tasks such as image retrieval. However, limited paired data and
arXiv:2602.01486v2 Announce Type: replace Abstract: Recent years have seen a surge in data-driven surrogates for dynamical systems that can be orders of magnitude faster than numerical solvers. Howeve
arXiv:2602.00844v2 Announce Type: replace-cross Abstract: Multivariate time series imputation is often compromised by mismatch between the observed and true data distributions, a bias induced by the c
arXiv:2512.05844v3 Announce Type: replace Abstract: Transformer-based autoregressive models offer an efficient alternative to diffusion- and flow-matching-based approaches for generating 3D molecules.
In the high-stakes world of digital infrastructure, speed isn't just a metric — it’s currency. At Google Cloud Next ‘26 we announced the Bigtable in-memory tier, a breakthrough for our fully managed c
arXiv:2605.04979v1 Announce Type: cross Abstract: A Tree Markov Decision Problem (T-MDP) is a finite-horizon MDP with a starting state s_{1}, in which every state is reachable from s_{1} through exact
arXiv:2605.05116v1 Announce Type: new Abstract: Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit sem
One of the things that made the Mythos release hard to interpret is that Anthropic held back details on most vulns they found, to give defenders time to patch. 1 month later, info from orgs with acces
arXiv:2605.04450v1 Announce Type: cross Abstract: Generative Recommender (GR) inference places embedding hot caches (EMB) and KV caches in direct competition for limited GPU HBM: allocating more memor
arXiv:2605.03762v1 Announce Type: new Abstract: Large language models are moving from static text generators toward real-world decision-support systems, where forecasting is a composite capability tha
arXiv:2605.05084v1 Announce Type: new Abstract: Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address this b
arXiv:2506.07548v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning (MARL) has reached competitive performance on cooperative tasks against scripted adversaries, yet most meth
In this post, you will learn how to implement reinforcement learning with verifiable rewards (RLVR) to introduce verification and transparency into reward signals to improve training performance. This
arXiv:2603.22844v4 Announce Type: replace Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-b
arXiv:2511.16567v3 Announce Type: replace Abstract: In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordi
arXiv:2605.04564v1 Announce Type: new Abstract: The representativeness of synthetic pre-crash scenarios is crucial for assessing the safety impact of Driving Automation Systems through virtual simulat
arXiv:2605.04215v1 Announce Type: new Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative AI, offering fully parallel token generation that can lead t
arXiv:2605.05040v1 Announce Type: new Abstract: On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a st
arXiv:2601.09195v3 Announce Type: replace Abstract: Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional S
arXiv:2605.05081v1 Announce Type: new Abstract: We consider the stabilization of Vlasov--Poisson plasma dynamics, a central control problem in nuclear fusion. Our focus is the gap between what an idea
arXiv:2505.18466v2 Announce Type: replace Abstract: Evaluations of Large Language Models (LLMs) often overlook intersectional and culturally specific biases, particularly in underrepresented multiling
arXiv:2604.03976v2 Announce Type: replace Abstract: Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI syste
arXiv:2508.04204v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) have demonstrated impressive performance in reasoning-intensive tasks, but they remain vulnerable to harmful content g
arXiv:2605.04920v1 Announce Type: cross Abstract: Compositional generalization refers to correctly interpret novel combinations of known primitives, which remains a major challenge. Existing approache
arXiv:2605.04242v1 Announce Type: new Abstract: Nationwide road-incident forecasting is a systems problem before it is a modeling problem. A usable service must connect historical incident archives, h
arXiv:2605.03409v1 Announce Type: new Abstract: We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that c
arXiv:2605.05112v1 Announce Type: new Abstract: SWE-bench-style agentic reinforcement learning relies on expensive stateful trajectories, yet substantial compute is wasted on sampled rollout groups wi
arXiv:2601.00264v2 Announce Type: replace Abstract: Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap be
arXiv:2601.08623v2 Announce Type: replace Abstract: Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from
arXiv:2605.04222v1 Announce Type: cross Abstract: Real-world control systems must achieve long-horizon objectives (liveness) while respecting continuous-time safety constraints, a combination that mot
arXiv:2502.04512v3 Announce Type: replace Abstract: AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability an
arXiv:2605.05008v1 Announce Type: cross Abstract: Regionalization aims to partition a spatial domain into contiguous regions that share similar characteristics, enabling more effective spatial analysi
arXiv:2509.17244v2 Announce Type: replace Abstract: We propose MADP, a novel diffusion-model-based approach for collaboration in decentralized robot swarms. MADP leverages diffusion models to generate
arXiv:2505.18118v2 Announce Type: replace-cross Abstract: Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledg
arXiv:2605.04202v1 Announce Type: new Abstract: Strategic classification studies the problem where self-interested individuals or agents manipulate their response to obtain favorable decision outcomes
arXiv:2505.19629v3 Announce Type: replace-cross Abstract: Self-adaptive robotic systems operate autonomously in dynamic and uncertain environments, requiring robust real-time monitoring and adaptive b