research

To be clear: 1. No it can't. I've used Fable while it was available, it was a good model but still less than 1% of the way there. 2. If it c…

researchfrancois-chollet--x

To be clear: 1. No it can't. I've used Fable while it was available, it was a good model but still less than 1% of the way there. 2. If it could, that fact would generally benefit SaaS companies, not

Research

Two of the most important biomedical breakthroughs came from science of the Gila lizard venom (GLP-1s) and yogurt (CRISPR genome editing). '…

DGX agent

Two of the most important biomedical breakthroughs came from science of the Gila lizard venom (GLP-1s) and yogurt (CRISPR genome editing). 'The system that turned that lizard into a medicine is now be

researchyann-lecun--x

22 Jun 2026

Use Case 3: One-Shot Blindfold Chess Can an AI hold an entire game state in memory without drifting? To test Fugu Ultra’s persona stability …

Use Case 3: One-Shot Blindfold Chess Can an AI hold an entire game state in memory without drifting? To test Fugu Ultra’s persona stability and sustained memory, we had it play 4 back-to-back games of

researchdavid-ha--x

Use Case 4: Computer Aided Design of Mechanical Iris Can an AI generate precise, functional mechanical designs? We tasked Fugu Ultra with cr…

Use Case 4: Computer Aided Design of Mechanical Iris Can an AI generate precise, functional mechanical designs? We tasked Fugu Ultra with creating a mechanical iris in CAD, similar to a camera apertur

researchdavid-ha--x

'We Have to Stop Freaking Out About A.I.' warns Nobel laureate Robert Shiller. Depressions, formerly called panics, are caused by self-fulfi…

'We Have to Stop Freaking Out About A.I.' warns Nobel laureate Robert Shiller. Depressions, formerly called panics, are caused by self-fulfilling fears (the only thing we have to fear is fear itself),

A slightly improved DVD-JEPA demo [P]

researchr-machinelearning

This post likely presents an enhanced demonstration of DVD-JEPA, a video variant of the Joint Embedding Predictive Architecture model. The JEPA framework has been extended to video tasks (V-JEPA) , an

🚨🚨🚨A standing ovation for the Washington Post, @wapo . 👏👏👏 You spent a full year investigating whether America's Director of National …

🚨🚨🚨A standing ovation for the Washington Post, @wapo . 👏👏👏 You spent a full year investigating whether America's Director of National Intelligence, the woman with access to every classified secret thi

Books are so OP

researchfrancois-chollet--x

Francois Chollet likely discusses why books are exceptionally valuable or 'overpowered' as learning and knowledge resources, possibly contrasting their effectiveness against other media or modern alte

Donald Trump will go down in history as the only US President to be outwitted by a single-celled organism.

I can't verify this as a factual statement suitable for a knowledge base. This appears to be a critical commentary or opinion about Donald Trump's handling of COVID-19, posted by AI researcher Yann Le

Fauci was a hero - he didn't kill millions, but he did save millions of lives. Highest paid? Hardly - he was a civil servant getting paid mu…

Fauci was a hero - he didn't kill millions, but he did save millions of lives. Highest paid? Hardly - he was a civil servant getting paid much less than had he gone into private practice. People like

Honored to welcome @iitbombay and BharatGen as founding contributors to Project Tapestry. India isn’t just adopting open & frontier AI — it’…

Honored to welcome @iitbombay and BharatGen as founding contributors to Project Tapestry. India isn’t just adopting open & frontier AI — it’s helping build it, in its own languages and on its own term

Signals of physical plausibility are hiding in the geometry of frozen image encoders. No video training. No physics supervision.

This work demonstrates that frozen image encoders (neural networks trained on static images without video or physics supervision) contain implicit geometric signals that correspond to physical plausib

So @jonswaine @washingtonpost has seen hundreds of documents containing evidence that Tulsi Gabbard, Donald Trump's Director of National Int…

So @jonswaine @washingtonpost has seen hundreds of documents containing evidence that Tulsi Gabbard, Donald Trump's Director of National Intelligence, was directed throughout her career by the leader

The dismantling of USAID has already ensued in roughly 600,000 deaths, about 400,000 of them children, in poor nations abroad, according to …

The dismantling of USAID has already ensued in roughly 600,000 deaths, about 400,000 of them children, in poor nations abroad, according to Boston University epidemiologist Brooke Nichols. The toll is

The hardest part of any task is overcoming the activation energy. The rest is just riding the momentum.

researchfrancois-chollet--x

This post from AI researcher François Chollet discusses the psychological principle that initiating a task requires the most effort (activation energy), while momentum carries you through the remainde

The Top AI Papers of the Week (June 14 - June 21): - PreAct - SpatialClaw - Back on Track - OpenClaw-Skill - From Trainee to Trainer - Compo…

The Top AI Papers of the Week (June 14 - June 21): - PreAct - SpatialClaw - Back on Track - OpenClaw-Skill - From Trainee to Trainer - Compositional Skill Routing - Can LLM Agents Infer World Models?

researchdair-ai--x

Anthony Fauci is an American hero who kept us protected from deadly viruses for decades. The people spreading lies about him are spreading R…

Anthony Fauci is an American hero who kept us protected from deadly viruses for decades. The people spreading lies about him are spreading Russian propaganda because they get paid to do so. They are t

20 Jun 2026

As India builds frontier AI rooted in its own languages and knowledge, IIT Bombay and BharatGen are proud to support and participate in Proj…

As India builds frontier AI rooted in its own languages and knowledge, IIT Bombay and BharatGen are proud to support and participate in Project Tapestry: an open, global consortium for nations to adva

20 Jun 2026

TSAuditor: A time-series auditing framework [P]

researchr-machinelearning

TSAuditor is a contamination auditing framework for time series foundation models that uses probe adaptation dynamics to detect when evaluation datasets may have been exposed during pretraining, valid

20 Jun 2026

3-Key-Input: Exploring the Theoretical Minimum Keys for Text Entry

arXiv:2606.11642v1 Announce Type: cross Abstract: How far can we reduce the number of physical keys if we endow an ambiguous keyboard with modern language models? Fewer keys increase hardware design f

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

arXiv:2606.12160v1 Announce Type: new Abstract: In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal lo

A Geometric Profile of Semantic Information in Text: Frame-Conditional Uniqueness and a Trade-Off Triangle for Scalar Summaries

arXiv:2606.11222v1 Announce Type: new Abstract: How much meaning does a text carry? Shannon's theory measures uncertainty over symbols and is intentionally indifferent to meaning, while pairwise metri

A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm.

A prior-free blind detection of information leakage from model predictions

arXiv:2606.11267v1 Announce Type: new Abstract: Data leakage -- contamination of a model with information unavailable at baseline -- is the dominant reproducibility failure in machine-learning-based s

A Resource for Enthymeme Detection in Controversial Political Discourse

arXiv:2606.12186v1 Announce Type: new Abstract: Enthymemes, arguments with unstated premises or conclusions, are pervasive in persuasive discourse, yet their annotation remains notoriously subjective.

A Riemannian Approach to Low-Rank Optimal Transport

arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing approaches rely heavily on first-order mirror-descent

A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks

arXiv:2606.11236v1 Announce Type: cross Abstract: Training deep spiking neural networks (SNNs) remains challenging due to sharp loss landscapes and temporal inconsistency caused by surrogate gradients

Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems

arXiv:2606.12337v1 Announce Type: cross Abstract: Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based opt

Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents

arXiv:2606.11219v1 Announce Type: cross Abstract: Audio language models (ALMs) are increasingly used for speech-based understanding, yet their ability to perform semantic reasoning beyond transcriptio

Agreement in Representation Space for Open-Ended Self-Consistency

arXiv:2606.12003v1 Announce Type: new Abstract: Self-consistency improves LLM reasoning by sampling multiple outputs and selecting the most consistent answer, but existing formulations largely rely on

AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory

arXiv:2602.02285v2 Announce Type: replace-cross Abstract: We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-e

An XAI View on Explainable ASP: Methods, Systems, and Perspectives

arXiv:2601.14764v2 Announce Type: replace Abstract: Answer Set Programming (ASP) is a popular declarative reasoning and problem solving approach in symbolic AI. Its rule-based formalism makes it inher

Analytic Bijections for Smooth and Interpretable Normalizing Flows

arXiv:2601.10774v2 Announce Type: replace Abstract: A key challenge in normalizing flows is finding expressive invertible scalar bijections. Existing approaches face trade-offs: affine transformations

Anatomically Conditioned Recurrent Refinement for Topology-Aware Circle of Willis Segmentation

arXiv:2606.12319v1 Announce Type: new Abstract: Segmenting the Circle of Willis (CoW) from Magnetic Resonance Angiography (MRA) is challenging due to complex topology and thin vascular structures that

Are LLMs Bad at Moral Reasoning?

arXiv:2606.11635v1 Announce Type: cross Abstract: For highly capable AI systems to operate safely in dynamic, open-ended environments, they must be able to identify, understand, and respond to moral r

Attention by Synchronization in Coupled Oscillator Networks

arXiv:2606.12059v1 Announce Type: new Abstract: We address transformer attention on energy-constrained physical substrates. Softmax attention requires exponentiation and global reduction, operations w

Autoregressive Direct Preference Optimization

arXiv:2602.09533v2 Announce Type: replace Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However,

Battery detection of XRay images using transfer learning

arXiv:2606.11779v1 Announce Type: new Abstract: The need for detecting and sorting batteries is drastically increasing for many applications. This study proves the potential of transfer learning in pr

Bergson: An Open Source Library for Data Attribution

arXiv:2606.11660v1 Announce Type: new Abstract: Data attribution is a promising field in interpretability that aims to explain model behavior through the influence of its training data, with applicati

Bernstein-Schur Kernels: Random Features by Sketched Modulation and Radial Randomization

arXiv:2606.11255v1 Announce Type: new Abstract: Bernstein--Schur kernels are products of a finite-feature kernel (one with an explicit finite-dimensional feature map) and a completely monotone shift-i

Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions

arXiv:2606.12171v1 Announce Type: new Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in prob

Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models

arXiv:2606.12273v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training me

Calibrating Decision Robustness via Inverse Conformal Risk Control

arXiv:2510.07750v3 Announce Type: replace-cross Abstract: Robust optimization safeguards decisions against uncertainty by optimizing against worst-case scenarios, yet their effectiveness hinges on a p

Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI

arXiv:2606.12210v1 Announce Type: new Abstract: Can financial news reliably predict short-term stock movements? Despite advances in large language models, this question remains unresolved. We revisit

Capacity-Constrained Online Convex Optimization with Delayed Feedback

arXiv:2606.11711v1 Announce Type: new Abstract: Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, trackin

Carbon-Aware Governance Gates: An Architecture for Sustainable GenAI Development

arXiv:2602.19718v2 Announce Type: replace-cross Abstract: The rapid adoption of Generative AI (GenAI) in the software development life cycle (SDLC) increases computational demand, which can raise the

Causal Emotion Recognition in Conversation: Context Saturation and Discourse-Marker Evidence

arXiv:2601.00181v3 Announce Type: replace-cross Abstract: We address two persistent gaps in Emotion Recognition in Conversation: which modeling choices materially affect performance, and how recogniti

CellNet -- Localizing Cells using Sparse and Noisy Point Annotations

arXiv:2606.12286v1 Announce Type: new Abstract: Counting living cells is an important step in many biological research workflows. Our collaborators at the Wellcome Sanger Institute study vital genes i