Knowledge catalogue
arXiv:2510.09450v2 Announce Type: replace Abstract: Low-light video enhancement (LLVE) is challenging due to noise, low contrast, and color degradation. While learning-based methods enable fast infere
arXiv:2605.23493v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without intr
arXiv:2602.13241v2 Announce Type: replace-cross Abstract: Emergency call-takers form the first operational link in public safety response, handling over 240 million calls annually while facing a susta
arXiv:2605.22883v1 Announce Type: new Abstract: Current AI energy benchmarks measure consumption at the granularity of a single model invocation or training run. For classical single-turn workloads th
arXiv:2603.07079v2 Announce Type: replace-cross Abstract: On-policy distillation is a promising approach for transferring knowledge between language models, where a student learns from dense token-lev
arXiv:2605.23412v1 Announce Type: new Abstract: While social media platforms, such as Twitter, provide a medium for large-scale opinion sharing during news events, it is manually impossible for indivi
arXiv:2605.23163v1 Announce Type: new Abstract: End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficie
arXiv:2605.22898v1 Announce Type: new Abstract: Federated learning protocols face a structural trilemma: canonical server-based aggregation~ite{mcmahan2017} creates a single point of failure and gradi
for the years it was the opposite bashing AI gets more views than it used to BECAUSE PEOPLE FIGURED OUT HOW GREEDY MOST OF THE TECH OLIGARCHS ARE. even the Pope felt it was time to speak out. Bashing
arXiv:2605.23218v1 Announce Type: new Abstract: Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly
arXiv:2605.23100v1 Announce Type: new Abstract: Legged robots carry an IMU, but the inertial solution drifts because consumer-grade IMUs are noisy. However, the feet create intermittent contacts with
arXiv:2605.23382v1 Announce Type: new Abstract: Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent application
From the Patrick Boyle Channel on YouTube discussing the upcoming SpaceX IPO: Based on its filing, SpaceX has lost ~ $37 Billion over 24 years. The worst performance of any company which has gone publ
arXiv:2605.23304v1 Announce Type: new Abstract: Hazard, as an abstract concept, is typically defined through cognitive-level logical reasoning rather than concrete examples. In contrast, existing haza
arXiv:2605.23903v1 Announce Type: new Abstract: Camera-controlled video generation has achieved remarkable progress in recent years. However, existing video-to-video re-rendering methods primarily rel
arXiv:2605.23551v1 Announce Type: cross Abstract: A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is di
🚨 Google DeepMind CEO Sir Demis Hassabis: “Today’s systems, are nowhere near [AGI]. Doesn’t matter how many Erdős problems you solve… I think it’s far, far from what a true invention or someone like a
arXiv:2605.22963v1 Announce Type: cross Abstract: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated prop
arXiv:2605.23696v1 Announce Type: new Abstract: Effectively managing Air Traffic Control Officer (ATCO) workload is crucial in maintaining operational safety. Group supervisors use tools that estimate
Great that so many of you have enjoyed my deconstructions of Elon, Zuckerberg, and that OpenAI dude, but this is much more important: ⚠️⚠️⚠️i don’t think most people understand the implications of the
Gary Marcus humorously suggests changing one's social media name to 'Kekius Maximus,' likely commenting on internet culture, meme terminology, or the absurdity of online personas. The post appears to
arXiv:2605.23320v1 Announce Type: new Abstract: Ventilator decision support requires sequential decisions that track evolving physiology and disease trajectories while respecting safety boundaries and
Gary Marcus comments on how widespread reporting of similar issues or problems across multiple companies can lead to a collapse of confidence or a 'bubble pop' in a particular sector or narrative. The
If you live in the UK, and care about the risk from superintelligence, please read below! URGENT: The UK Parliament just selected 20 MPs to introduce a bill of their choosing. This is an unprecedented
arXiv:2601.09600v3 Announce Type: replace-cross Abstract: Online information access (IA) platforms are targets of authoritarian capture. We explore the question of how to safeguard our platforms and e
arXiv:2605.23146v1 Announce Type: cross Abstract: Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assum
arXiv:2605.23847v1 Announce Type: new Abstract: Large behaviour models have transformed the field of robotic manipulation, but prohibitive data requirements have thus far prevented a revolution simila
arXiv:2604.05157v2 Announce Type: replace Abstract: Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evalu
interesting to listen to this years later. what held up? what changed? I had a podcast where I was fortunate to have amazing guests. This was just as GPT 3 came out. Despite LLMs exceeding so many exp
it’s great! you can pay for the infrastructure that will eventually take your jobs! and if it fails and the bubble bursts? you can bail the hyperscalers out, and watch your pension fund die. The CEO o
I've yet to see, or hear of a company that is winning against its competition, because said company is spending more on AI tools, or using it better than the competition. Ways I see companies win: - b
arXiv:2605.23650v1 Announce Type: cross Abstract: Human feedback often arrives as preferences rather than calibrated numeric rewards, motivating reinforcement learning from preferential feedback, also
“Like nuclear energy, AI must be at the service of all and of the common good. Decisions about technology must never be separated from conscience and responsibility.” I agree with this sentiment by @P
arXiv:2602.04431v2 Announce Type: replace Abstract: LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fai
arXiv:2605.22900v1 Announce Type: new Abstract: Mediative Fuzzy Logic was conceived as a practical scheme for reconciling hesitant or conflicting assessments in fuzzy control and decision-making. Howe
arXiv:2605.23064v1 Announce Type: new Abstract: Body shape and circumferences are clinically informative biomarkers for risk stratification, including measures such as waist to hip ratio, limb and tru
arXiv:2605.23482v1 Announce Type: cross Abstract: Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increas
Musk hates Altman because Altman deceived him. Altman hates Musk because Musk is an egomaniac. LeCun (who is an equally big egomaniac) hates Musk because Musk is a jerk. Musk hates LeCun because LeCun
arXiv:2605.23420v1 Announce Type: new Abstract: Social norms reflect shared expectations on acceptable behavior. Measuring social norms alignment remains challenging, with existing approaches typicall
arXiv:2511.14286v2 Announce Type: replace Abstract: In computer- and robot-assisted orthopedic surgery (CAOS), patient-specific surgical plans derived from preoperative imaging define target locations
arXiv:2605.22874v1 Announce Type: new Abstract: Effectively translating between natural language (NL) and formal logics like Linear Temporal Logic (LTL) requires expertise that limits formal verificat
arXiv:2511.05963v2 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Conse
arXiv:2605.23715v1 Announce Type: new Abstract: Natural Language Generation (NLG) evaluation has changed dramatically since 1990, and will continue to evolve in the future. In 1990, when NLG had close
arXiv:2605.23819v1 Announce Type: cross Abstract: A central question in computational vision is whether human-like visual representations are better explained by discriminative or generative learning.
Gary Marcus and David Sacks found common ground on an unspecified topic, as indicated by Marcus's post on X (formerly Twitter). Without access to the full thread context, the specific point of agreeme
arXiv:2508.14311v2 Announce Type: replace-cross Abstract: There is an increasing need to enforce multiple, often competing, measures of fairness within automated decision systems. The appropriate weig
arXiv:2605.23145v1 Announce Type: cross Abstract: Individual fairness, the notion that 'similar individuals should be treated similarly,' provides a strong and flexible fairness guarantee for algorith
People are often confused that I am against the framing of 'tool AI' This is hands down the best post explaining (some of) the issues with the term. Give it a read! Many in AI safety advocacy argue th
people in glass houses should not throw stones, Zuck Mark Zuckerberg says Apple's lack of innovation since the iPhone will lead to its decline 'They haven't really invented anything great in a while.
arXiv:2605.23128v1 Announce Type: new Abstract: Currently, Vision-Language-Action (VLA) models have become the most adopted paradigm for robotic manipulation for its great potential for task generaliz
arXiv:2605.22856v1 Announce Type: cross Abstract: Channel foundation models assume access to fully observed channels, an assumption that fails in deployment. We introduce PilotWiMAE, a self-supervised
arXiv:2605.23027v1 Announce Type: new Abstract: Recent research has demonstrated the potential of reinforcement learning in effective multi-robot collaboration, particularly in social dilemmas where r
arXiv:2605.23856v1 Announce Type: new Abstract: Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance f
Pope Leo has warned that the artificial intelligence revolution is being driven primarily by profit motives rather than ethical considerations, characterizing this as a form of 'idolatry of profit.' T
arXiv:2605.23522v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.
arXiv:2605.23351v1 Announce Type: new Abstract: We study adversarial multi-armed bandits with and without delayed feedback under a safety-aware goal: achieving minimax-optimal worst-case regret while
arXiv:2605.23182v1 Announce Type: new Abstract: Pure exploration in episodic Reinforcement Learning has primarily focused on Best Policy Identification (BPI), which seeks to identify a (near)-optimal
arXiv:2510.11195v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminatin
arXiv:2605.22833v1 Announce Type: cross Abstract: Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Trad
arXiv:2605.11215v2 Announce Type: replace-cross Abstract: Pre-training large language models on massive GPU clusters has made hardware faults routine rather than rare, driving the need for resilient t