Knowledge catalogue
arXiv:2604.09213v1 Announce Type: new Abstract: Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong pro
arXiv:2604.09487v1 Announce Type: cross Abstract: Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition. Still, these systems
arXiv:2602.04418v3 Announce Type: replace-cross Abstract: We present SPEAR, a multi-agent coordination framework for smart contract auditing that applies established MAS patterns in a realistic securi
arXiv:2604.08865v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard tok
arXiv:2511.04256v2 Announce Type: replace Abstract: As a key component of large language model (LLM) post-training, Reinforcement Learning from Verifiable Rewards (RLVR) has substantially improved rea
arXiv:2604.08905v1 Announce Type: new Abstract: Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization
arXiv:2509.25210v3 Announce Type: replace-cross Abstract: To gain finer regional forecasts, many works have explored the regional integration from the global atmosphere, e.g., by solving boundary equa
arXiv:2604.08620v1 Announce Type: cross Abstract: Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-differenc
arXiv:2602.17330v3 Announce Type: replace-cross Abstract: Comparative analysis of adaptive immune repertoires at population scale is hampered by two practical bottlenecks: the near-quadratic cost of p
With AI capabilities rapidly increasing, humans appear close to developing AI systems that are better than human experts across all domains. This raises a series of questions about how the world will—
arXiv:2604.09271v1 Announce Type: new Abstract: The transition to electric mobility hinges on maximising aggregate adoption while also facilitating equitable access. This study examines whether the 'c
arXiv:2601.23045v2 Announce Type: replace Abstract: As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task sc
The trend of treating all of AI as One Big Thing that always includes data centers & job changes & education changes & power & accelerating science & misinformation & national security & corporate con
arXiv:2601.01580v2 Announce Type: replace-cross Abstract: Self-reflection capabilities emerge in Large Language Models after RL post-training, with multi-turn RL achieving substantial gains over SFT c
'There is no advantage from being first. If you get first to a superintelligence you don't control, the superintelligence wins. Not the USA. Not China. Not the UK.' @andreamiotti of @ControlAI & TBC o
arXiv:2604.09150v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks by leveraging long Chain-of-Thought (CoT), but often suffer from overthinking,
arXiv:2604.09368v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed as scalable user simulators for recommender system evaluation. Yet existing simulators per
arXiv:2604.09439v1 Announce Type: cross Abstract: In this paper, we propose a sequential recommendation model that integrates Time-aware personalization, Multi-interest personalization, and Explanatio
arXiv:2604.09057v1 Announce Type: new Abstract: Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible moti
arXiv:2604.09519v1 Announce Type: new Abstract: World models have emerged as a unifying paradigm for learning latent dynamics, simulating counterfactual futures, and supporting planning under uncertai
arXiv:2603.08146v3 Announce Type: replace Abstract: Existing frameworks for gradient-based training of spiking neural networks face a trade-off: discrete-time methods using surrogate gradients support
arXiv:2510.00491v3 Announce Type: replace-cross Abstract: Learning diverse manipulation skills for real-world robots is severely bottlenecked by the reliance on costly and hard-to-scale teleoperated d
arXiv:2604.09159v1 Announce Type: new Abstract: Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy para
arXiv:2604.08550v1 Announce Type: cross Abstract: Fake orders pose increasing threats to sequential recommender systems by misleading recommendation results through artificially manipulated interactio
arXiv:2604.09169v1 Announce Type: new Abstract: Semi-supervised semantic segmentation in computational pathology remains challenging due to scarce pixel-level annotations and unreliable pseudo-label s
arXiv:2604.09330v1 Announce Type: cross Abstract: Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-wo
Violence is not the answer. But maybe boycotts are? 🚨 NOW: The FBI is RAIDING the home of a 20-year-old man who threw a molotov cocktail at the home of OpenAI CEO Sam Altman Over a DOZEN federal agent
arXiv:2604.09508v1 Announce Type: cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents. To tackle complex qu
arXiv:2604.09349v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly advanced the reasoning ability of vision-language models (VLMs). However, the
Boris Cherny and colleagues conducted cybersecurity evaluations of Claude Mythos Preview, finding it to be the first AI model to successfully complete an AISI (AI Safety Institute) cyber range end-to-
arXiv:2602.17667v2 Announce Type: replace-cross Abstract: In video search systems, user historical behaviors provide rich context for identifying search intent and resolving ambiguity. However, tradit
arXiv:2604.08728v1 Announce Type: new Abstract: Cooperation in multi-agent reinforcement learning (MARL) benefits from inter-agent communication, yet most approaches assume idealized channels and exis
arXiv:2603.15757v2 Announce Type: replace-cross Abstract: What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from
I just love the language of this study...it speaks of the shifting 'community language'...and that is so true...have you noticed the new 'community language' is 'harness', it was 'contextual prompting
Maggie Eastland / Bloomberg: Sources: the US' AI chip export push risks being undermined by licensing bottlenecks, staff attrition, and unclear policy at the Bureau of Industry and Security — Presiden
Wow, time for a social media detox. Just today - a call for violence against me - insults (that’s every day) - flagrant lies about my credentials - claims that I advocated violence when i repeatedly c
After @aiDotEngineer, which was full of useful criticism, I remembered that the most confident takes on AI often came from the least exposure. Rejection is easy, trial and error is expensive. I wrote
An angel investor reportedly called for violence against AI skeptic Gary Marcus, who has consistently and publicly advocated against violent responses, instead promoting boycotts as a form of protest.
At this point how can anybody take seriously @sama’s claim that “Working towards prosperity for everyone, empowering all people, and advancing science and technology are moral obligations for me”, whe
Auto-generated index of all companies mentioned across the wiki.
Gary Marcus, an AI researcher and cognitive scientist, posted a tweet advocating for a boycott as a nonviolent, non-confrontational form of protest or opposition against an unnamed individual. The pos
@GaryMarcus @sama the gap between altmans public statements and openais actual behavior has been widening steadily for 2 years now. at some point 'we want to benefit humanity' and 'we want zero liabil
👇 “I still maintain that LLMs are really dumb and of limited use. it’s my opinion as a practitioner and professional that the hype being peddled by the AI corporations and self promoters (from X grift
memory isn't a retrieval widget. it's write policy. the harness decides what survives compaction, what gets promoted, and what becomes reusable state. https://x.com/hwchase17/status/204297850056760973
postscript: Violence is not the answer. Boycott is the answer. This one’s easy. There is ample evidence that Altman is a dishonest person with inordinate power that we should not trust. But the way fo
@sterlingcrispin @sama Violence was unjustified, and i don’t support it. But many many people may die at Altman’s hands and it is important to speak out when he lies about his moral stance. The headli
Violence is not the answer. Boycott is the answer. This one’s easy. There is ample evidence that Altman is a dishonest person with inordinate power that we should not trust. But the way forward to is
What happened to Sam Altman and his family is really awful. It is hard to reconcile his call to “de-escalate the rhetoric and tactics” with his implication that a piece of critical journalism (Ronan F
Gary Marcus, a cognitive scientist and AI critic, posted on X criticizing the platform's search functionality, arguing it is poorly designed for classifying and surfacing trends. He contrasts its inad
You know when you’re making the right calls when the haters start to get louder. We may not always see to eye on everything, I tend to encourage development in areas that you don’t but I still highly
arXiv:2604.04614v2 Announce Type: replace-cross Abstract: Deep learning-based modeling of multimodal Electronic Health Records (EHRs) has become an important approach for clinical diagnosis and risk p
A cry for the kind of extreme unfettered capitalism that could get us all killed and make all of @ESYudkowsky’s worst nightmares come true. AI needs open markets and open access not whatever is happen
arXiv:2604.06940v1 Announce Type: cross Abstract: Most neural solvers for the Traveling Salesperson Problem (TSP) are trained to output a single solution, even though practitioners rarely stop there:
arXiv:2604.07395v1 Announce Type: cross Abstract: Robotic manipulation systems that follow language instructions often execute grasp primitives in a largely single-shot manner: a model proposes an act
arXiv:2408.05086v3 Announce Type: replace Abstract: Neural language models (LMs) have been shown to capture complex linguistic patterns, yet their utility in understanding human language and more broa
arXiv:2604.07480v1 Announce Type: new Abstract: Reward machines are automaton-like structures that capture the memory required to accomplish a multi-stage task. When combined with reinforcement learni
arXiv:2604.08534v1 Announce Type: new Abstract: Large-scale real-world robot data collection is a prerequisite for bringing robots into everyday deployment. However, existing pipelines often rely on s
arXiv:2512.10510v2 Announce Type: replace-cross Abstract: Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collecte
arXiv:2604.07007v1 Announce Type: cross Abstract: Autonomous AI agents are beginning to operate across organizational boundaries on the open internet -- discovering, transacting with, and delegating t
arXiv:2604.06566v1 Announce Type: cross Abstract: As the complexity of modern workloads and hardware increasingly outpaces human research and engineering capacity, existing methods for database perfor