Knowledge catalogue
arXiv:2606.04767v1 Announce Type: cross Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack
arXiv:2511.07107v3 Announce Type: replace Abstract: Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address im
Sarah Perez / TechCrunch: Meta's Oversight Board says Meta's account deactivations lack due process, violations are flagged without clarity, and there's little support for appeals — Meta's Oversight B
arXiv:2606.04413v1 Announce Type: new Abstract: Helpful-only models, that is, models that are trained to always follow user intent, are valuable for dangerous capability evaluations and other areas of
arXiv:2606.04231v1 Announce Type: cross Abstract: Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing
This article discusses methods and tools for evaluating routing policies in machine learning models, likely covering techniques to validate that model routing decisions are effective and functioning a
arXiv:2606.04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution het
arXiv:2606.04158v1 Announce Type: new Abstract: Multi-agent Next-Best-View (NBV) selection for safe path planning in uncertain and unknown environments requires informative, safety-aware, and efficien
arXiv:2606.04847v1 Announce Type: cross Abstract: Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggl
arXiv:2606.04562v1 Announce Type: new Abstract: Purpose The WHO's COVID-19 non-pharmaceutical interventions (e.g., lockdowns, vaccinations) effectively curb transmission but impose heavy economic stra
arXiv:2606.04820v1 Announce Type: cross Abstract: CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faith
arXiv:2606.04483v1 Announce Type: new Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the real failure mo
Offering a “damn, I’m truly impressed” award, for the first person or team to build a domain-general AI system that can play @baldursgate3, start to finish. Will make the prize especially sweet if you
Offering @kevinroose $100,000 bet that no domain-general AI system can do this before his book comes out. (mimicking walkthroughs doesn’t count.) Offering a “damn, I’m truly impressed” award, for the
arXiv:2603.28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of vari
arXiv:2606.04092v1 Announce Type: new Abstract: Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via o
arXiv:2601.07144v3 Announce Type: replace-cross Abstract: Ensuring fairness in matching algorithms is a key challenge in allocating scarce resources and positions. Focusing on Optimal Transport (OT),
arXiv:2606.04463v1 Announce Type: new Abstract: We present OSCAR, a precise action-conditioned video world model that generalizes across different robot embodiments and enables robot policy evaluation
arXiv:2601.15158v4 Announce Type: replace-cross Abstract: Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermed
arXiv:2601.07408v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) has emerged as a promising critic-free reinforcement learning paradigm for reasoning tasks. However, stand
arXiv:2602.19799v2 Announce Type: replace-cross Abstract: Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network
arXiv:2606.04226v1 Announce Type: cross Abstract: Simulation environments are useful for both robot policy learning and planning verification and validation. Traditionally, the process of creating a s
arXiv:2606.04780v1 Announce Type: new Abstract: Persistent LLM agents require memory representations that make the formation of person understanding explicit across long term interaction. Existing age
arXiv:2606.04143v1 Announce Type: cross Abstract: Accurate flood forecasting is essential for mitigating disaster risks and protecting communities. However, purely data-driven machine learning models
arXiv:2606.04599v1 Announce Type: new Abstract: Large language model (LLM) agents have shown promise in automating complex data-analysis workflows, but their reliable deployment remains challenging in
arXiv:2602.23214v2 Announce Type: replace Abstract: Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained gen
arXiv:2606.04095v1 Announce Type: cross Abstract: Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quali
arXiv:2606.04335v1 Announce Type: new Abstract: The framework of robust Markov decision processes (RMDPs) allows the design of reinforcement learning agents that satisfy performance guarantees under w
arXiv:2606.04968v1 Announce Type: new Abstract: Large vision-language-action (VLA) policies are increasingly trained as conditional generative models over action chunks. Yet deployment produces mixed-
arXiv:2606.04978v1 Announce Type: new Abstract: LLMs can appear cautious in risk decision-making tasks, yet cautious-looking outputs do not necessarily indicate alignment with human decision-making me
This post likely discusses concerns about AI systems that merely imitate or reproduce existing walkthroughs and instructional content rather than demonstrating genuine understanding or original proble
arXiv:2004.10846v5 Announce Type: replace-cross Abstract: Problem definition: Traditionally, New York City's top 8 public schools have selected candidates solely based on their scores in the Specializ
arXiv:2606.04380v1 Announce Type: cross Abstract: Forecast reconciliation usually starts from a fixed measurement system and asks how forecasts should be projected onto a coherent space. We ask a diff
arXiv:2606.05152v1 Announce Type: cross Abstract: Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sam
Remember when Dario called pausing AI 'most extreme'? '...we should just pause ... that extreme position doesn't make much sense to me either.' Anthropic now: 'We believe it would be good for the worl
arXiv:2606.05109v1 Announce Type: new Abstract: To leverage the full potential of multimodal data, we need representations that go beyond the state-of-the-art alignment and fusion approaches and explo
arXiv:2606.04210v1 Announce Type: cross Abstract: Randomized smoothing (RS) certifies robustness in the vector space where Gaussian noise is added. In audio classification, this space is often not uni
arXiv:2606.04923v1 Announce Type: cross Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models
arXiv:2606.04703v1 Announce Type: new Abstract: Experience internalization converts contextual experience from past interactions into reusable parametric capability, offering a promising path toward c
arXiv:2606.04387v1 Announce Type: cross Abstract: Sales lead conversion in high-stakes domains (e.g., automotive, real estate) differs fundamentally from e-commerce recommendation due to prolonged dec
arXiv:2506.06178v3 Announce Type: replace Abstract: Policy gradient (PG) methods are a class of effective reinforcement learning algorithms, particularly when dealing with continuous control problems.
arXiv:2606.04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and supervised fine-tuning (SFT). We question this status
arXiv:2502.01576v2 Announce Type: replace Abstract: Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations that can induce h
arXiv:2606.04248v1 Announce Type: new Abstract: Decentralized rigid formation flocking requires a swarm of autonomous agents to maintain a predetermined geometric configuration while moving, relying s
arXiv:2606.04051v1 Announce Type: cross Abstract: The evolution of LLMs into tool-enabled agents creates a new class of safety challenges associated with real-world execution rather than simple text g
arXiv:2606.04536v1 Announce Type: new Abstract: Existing memory-augmented LLM agents store past experience exclusively in prompt space, as textual summaries or retrieved passages, while keeping model
arXiv:2606.04812v1 Announce Type: cross Abstract: Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep R
See also: https://x.com/emollick/status/1799046218917822682?s=20 Alignment, of a sort: this paper conducts what they call a “moral Turing Test,” asking people to compare GPT-4o to humans on ethical qu
arXiv:2512.08094v2 Announce Type: replace Abstract: The goal of this work is to develop a universal approach for aligning subtitles (i.e., spoken language text with corresponding timestamps) to contin
arXiv:2606.04373v1 Announce Type: cross Abstract: Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attenti
arXiv:2606.04036v1 Announce Type: new Abstract: On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense su
arXiv:2512.21917v3 Announce Type: replace-cross Abstract: Policy alignment to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., Bradley-Ter
shit is getting real Sam Altman, Dario Amodei, Demis Hassabis and many others have signed a letter urging Congress to increase security on orders of synthetic nucleic acids - and the equipment needed
arXiv:2510.13704v2 Announce Type: replace-cross Abstract: Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment paralleliz
arXiv:2606.04167v1 Announce Type: cross Abstract: We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro system
arXiv:2606.04155v1 Announce Type: cross Abstract: Social skills such as negotiation and leadership are crucial for personal and professional success in today's interconnected world. However, scalable
arXiv:2505.11166v3 Announce Type: replace-cross Abstract: Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-
arXiv:2511.20102v3 Announce Type: replace Abstract: Sparse attention reduces the quadratic complexity of full self-attention but faces two challenges: (1) an attention gap, where applying sparse atten
Starmer is right about this; would be ironic if the net of it was to keep Starmer in power for longer. British Prime Minister Keir Starmer has accused Elon Musk of 'whipping up division' and interferi
arXiv:2606.04150v1 Announce Type: new Abstract: Public discourse and emerging policy typically assume that AI emotional support is a deliberate act: a lonely user consciously seeking comfort from a de