Knowledge catalogue
arXiv:2605.04874v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) has proven to be an effective solution for mitigating hallucination in Multimodal Large Language Models (MLLMs) b
arXiv:2605.03598v2 Announce Type: cross Abstract: Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine l
arXiv:2505.11815v2 Announce Type: replace Abstract: Current vision-language models have been explored for multi-modal embedding tasks like information retrieval. However, they face significant challen
arXiv:2605.04732v1 Announce Type: new Abstract: Simulation-based planning with rollouts is a widely-deployed technique for decision making in stochastic environments. The primary instrument of simulat
arXiv:2512.05226v2 Announce Type: replace Abstract: Domain shift remains a key challenge in deploying machine learning models to the real world. Unsupervised domain adaptation (UDA) aims to address th
What happens when AIs become smarter than us? Why would they keep humans around if given the choice? Our new paper argues that only trying to control AIs is a limited strategy, and that a stable, mutu
arXiv:2605.05172v1 Announce Type: new Abstract: Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement af
arXiv:2605.04972v1 Announce Type: new Abstract: Aligning large language models with expert judgment is especially difficult in subjective evaluation tasks, where experts may disagree, rely on tacit cr
Wow this paper has been “just published” many times for nearly a year. I have called out at least two other “influencers” for the same thing on the same paper, including another one earlier this week.
yep, really embarassing One of the richest VCs, Marc Andreessen, has shown again that he thinks generative AI works perfectly well if you use the right prompts, thus ignoring the statistical nature of
100% stood the test of time: “What Ilya saw” was Sam’s bad behavior, not AGI. When Altman got fired “What did Ilya see?” became a wildly popular conspiracy meme. I think we can safely say now that wha
arXiv:2605.03787v1 Announce Type: new Abstract: Labeling medical images is a major bottleneck in the field of medical imaging, as it requires domain-specific expertise, and it gets further complicated
arXiv:2605.03262v1 Announce Type: new Abstract: We introduce the Yat kernel $k_{b,arepsilon}(mathbf{w},mathbf{x})=frac{(mathbf{w}^opmathbf{x}+b)^2}{|mathbf{x}-mathbf{w}|^2+arepsilon},qquad bge 0, arep
Jon Brodkin / Ars Technica: A US appeals court strikes down a 2023 FCC rule banning broadband access discrimination based on income, race, and more; Chair Brendan Carr welcomes the ruling — An appeals
arXiv:2605.00968v1 Announce Type: cross Abstract: Positional encoding plays a pivotal role in determin?ing the extrapolation and generalization performance of wireless foundation models for channel st
arXiv:2605.03212v1 Announce Type: cross Abstract: Modeling latent clinical constructs from unconstrained clinical interactions is a unique challenge in affective computing. We present ADAPTS (Agentic
arXiv:2605.02911v1 Announce Type: new Abstract: Future sixth-generation (6G) mobile networks are envisioned to be equipped with a diverse set of powerful, yet highly specialized, optimization experts.
arXiv:2509.20789v4 Announce Type: replace Abstract: The remarkable success of modern AI has been closely tied to scaling laws, yet the finite supply of high-quality data makes data efficiency--learnin
🚨Alphabet GOOGL trades at 133x free cash flow. For context: its pre-COVID multiple was ~20x. And free cash flow hasn't grown since 2021. GQG Partners — one of the world's top institutional investors —
Am I right that hyperscaling compute is the biggest bet in history? Any counter examples? It’s way more expensive than the Manhattan Project, the Apollo project, and railways across the US. If it does
Amazing the shit X gave me in November 2023 for saying Sam wasn’t always candid. He wasn’t. Period. Murati testified that, by fall 2023, Sam Altman was “not always” candid with her, and undermined her
And how many times have I told you that Sam is no longer the right CEO for OpenAI? Murati: My issues with Sam were very much around management and providing direction to the organization and decision
Anthropic: Anthropic researchers detail “model spec midtraining”, which adds a stage between pretraining and fine-tuning to improve generalization from alignment training — Sara Price2, Samuel Marks2,
arXiv:2605.03222v1 Announce Type: new Abstract: Activation-alignment measures such as Representational Similarity Analysis (RSA), Canonical Correlation Analysis (CCA), and Centered Kernel Alignment (C
arXiv:2605.03452v1 Announce Type: new Abstract: High-quality data collection is a fundamental cornerstone for training humanoid whole-body visuomotor policies. Current data acquisition paradigms predo
arXiv:2512.04277v3 Announce Type: replace Abstract: Post-training with reinforcement learning (RL) typically optimizes a single scalar objective and ignores structure in how solutions are produced. We
arXiv:2601.00421v2 Announce Type: replace Abstract: This paper explores how semantic-space reasoning, traditionally used in computational linguistics, can be extended to tactical decision-making in te
arXiv:2605.01758v1 Announce Type: new Abstract: Large multimodal model-based Multi-Agent Systems (MASs) enable collaborative complex problem solving through specialized agents. However, MASs are vulne
C’mon BBC. Zilis was sharp as a tack on the stand, on her role in the OpenAI *nonprofit* board, and how she managed conflicts as they began to develop, and this (which is not really even news since it
arXiv:2605.02734v1 Announce Type: new Abstract: Learning to Defer (L2D) enables a model to predict autonomously or defer to an expert, but prior work largely assumes flat label spaces. We study the fi
Gary Marcus clarifies that in the legal proceeding he's discussing, the jury serves an advisory role while the judge retains decision-making authority on the case outcome. Marcus expresses confidence
arXiv:2605.02658v2 Announce Type: new Abstract: Shortcut learning causes deep learning models to rely on non-essential features within the data. However, its formation in deep neural network training
arXiv:2602.20078v3 Announce Type: replace-cross Abstract: Scaling cooperative multi-agent reinforcement learning (MARL) is fundamentally limited by cross-agent noise. When agents share a common reward
arXiv:2605.03327v1 Announce Type: new Abstract: Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relat
arXiv:2605.03408v1 Announce Type: new Abstract: Reinforcement learning systems rely on environment interfaces that specify observations and reward functions, yet constructing these interfaces for new
arXiv:2605.03877v1 Announce Type: new Abstract: Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Dif
@Dr_Gingerballs At least actual ponzi schemes don't light their cash on fire... they just cant meet redemptions at the level of their inflated fake earnings. After all of the hyperscalers burn every l
arXiv:2605.03425v1 Announce Type: new Abstract: Differentially private (DP) training protects individual examples by adding noise to gradients, but the injected noise interacts nontrivially with adapt
arXiv:2605.03465v1 Announce Type: cross Abstract: Large language models have driven major advances in Text-to-SQL generation. However, they suffer from high computational cost, long latency, and data
arXiv:2602.14012v2 Announce Type: replace-cross Abstract: The integration of LLMs into vulnerability detection (VD) has shifted the field toward more interpretable and context-aware analysis. While po
@GaryMarcus I can't believe this is still a thing that 'experts' haven't caught up with. @GaryMarcus has been saying this forever, and those of us who have actually dug into the tech, analyzed it, use
arXiv:2507.07982v2 Announce Type: replace Abstract: Videos inherently represent 2D projections of a dynamic 3D world. However, our analysis suggests that video diffusion models trained solely on raw v
arXiv:2605.03163v1 Announce Type: new Abstract: Scientific time series often encode predictive geometric structure, including connectivity, cycles, shell-like geometry, directional changes, and nonlin
arXiv:2605.03377v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to whi
arXiv:2605.01482v1 Announce Type: new Abstract: Multi-Hop Fact Verification (MHFV) necessitates complex reasoning across disparate evidence, posing significant challenges for Large Language Models (LL
arXiv:2605.03403v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It ra
arXiv:2605.02943v1 Announce Type: new Abstract: Clinical reasoning demands multi-step interactions -- gathering patient history, ordering tests, interpreting results, and making safe treatment decisio
arXiv:2605.02919v1 Announce Type: new Abstract: Urban bridge networks are critical infrastructure whose disruption can cascade into severe impacts on transportation, emergency services, and economic a
arXiv:2603.00977v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents have recently demonstrated strong capabilities in interactive decision-making, yet they remain fundamentally
How Sam ('You parachute him onto a cannibal island, and he comes back five years later as king”) Altman operates: counsel: 'by fall of 2023 did you percieve altman was not candid with you? truthful? h
I repeat, the bubble is in the 'e' not the 'p' in today's PE ratios. The hucksters and talking heads will, as always, fail to realize until it's too late. But it's a very simple set up. Hyperscalers g
If Forbes had only waited to hear the testimony at this week’s trial Or read @_KarenHao’s book Or @RonanFarrow’s @newyorker investigation Or my own writings since fall 2023 They would have realized ho
Important nuance: the jury at this Musk-OpenAI trial is an *advisory* jury, hence not binding on the judge, and is only looking at liability (not damages, if any). Thanks to @bahhradx for correcting a
arXiv:2605.02175v1 Announce Type: new Abstract: The Legg--Hutter universal intelligence measure provides a rigorous scalar assessment of general intelligence as expected reward across all computable e
arXiv:2605.03641v1 Announce Type: new Abstract: Consumer robotics demands consolidation of safety-critical control, perception pipelines, and user applications on shared multicore platforms. While sta
just want to go back to how much intense pushback i got on this story at all levels of the company at the time, and how people speak very differently when under the threat of perjury lot of names etch
arXiv:2605.01790v1 Announce Type: cross Abstract: A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first mod
arXiv:2605.04040v1 Announce Type: new Abstract: Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM bac
Tim Harford compares large language models to tricksters, arguing that LLMs excel at generating plausible-sounding text without necessarily ensuring accuracy or truthfulness. The article likely explor
arXiv:2605.03299v1 Announce Type: new Abstract: Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and