Knowledge catalogue
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
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
'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),
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 Intelligence, the woman with access to every classified secret thi
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
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’s helping build it, in its own languages and on its own term
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 Boston University epidemiologist Brooke Nichols. The toll is
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?
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
Good idea For years, I raised alarms about dangerous gain-of-function research being farmed out to foreign countries, and I was told it was a conspiracy theory. Now, declassified documents show that t
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
Over the last two weeks, both the U.S. Government and Anthropic took significant actions that demonstrated their power to control access to AI by restricting what others can do with frontier models. T
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
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
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
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.
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
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.
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
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
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
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
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
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
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
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
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
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,
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
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
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
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
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
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
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
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
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
arXiv:2507.11688v4 Announce Type: replace Abstract: Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionalit
arXiv:2602.06868v2 Announce Type: replace Abstract: Zero-order optimization has recently received significant attention for designing optimal trajectories and policies for robotic systems. However, mo
arXiv:2606.12411v1 Announce Type: new Abstract: Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with
arXiv:2507.23534v3 Announce Type: replace-cross Abstract: Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience
arXiv:2512.16415v3 Announce Type: replace Abstract: Object counting in complex scenes is particularly challenging in the zero-shot (ZS) setting, where instances of unseen categories are counted using
arXiv:2601.11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable
arXiv:2506.20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across
arXiv:2509.19463v2 Announce Type: replace Abstract: A central challenge for multi-robot systems is fusing independently gathered perception data into a unified representation. Despite progress in Coll
arXiv:2606.11326v1 Announce Type: new Abstract: Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation fro
arXiv:2606.12088v1 Announce Type: new Abstract: Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information
arXiv:2606.11953v1 Announce Type: new Abstract: Hateful videos have become prevalent on online platforms, highlighting an urgent need for effective detection. However, existing studies primarily focus
arXiv:2606.11469v1 Announce Type: cross Abstract: We study the task of density estimation, where we hope to accurately estimate a probability density from n samples. A textbook method for density esti
arXiv:2606.12400v1 Announce Type: new Abstract: Long input sequences are central to document understanding and multi-step reasoning in Large Language Models, yet the quadratic cost of attention makes
arXiv:2603.09715v2 Announce Type: replace Abstract: Visual instruction tuning is crucial for improving vision-language large models (VLLMs). However, many samples can be solved via linguistic patterns
arXiv:2606.12189v1 Announce Type: new Abstract: We address 4D reconstruction from partial point cloud sequences, where depth-sensor observations are incomplete, unordered, and lack explicit temporal c
arXiv:2606.11710v1 Announce Type: new Abstract: This paper presents ERN-Net, an Evolving Reason Node-Net for efficient document image binarization. ERN-Net enhances degradation-sensitive regions, such
arXiv:2606.11471v1 Announce Type: cross Abstract: The expansion of the digital domain has resulted in a substantial increase in digital communication, with email emerging as one of the most prominent
arXiv:2606.11285v1 Announce Type: new Abstract: Unauthorized unmanned aerial vehicle (UAV) activity around airports, public venues, and other sensitive sites has made protected-airspace monitoring inc
arXiv:2606.11450v1 Announce Type: new Abstract: Recently, masked skeleton reconstruction models have emerged as strong action representation learners, driving significant progress in self-supervised s
arXiv:2505.17623v2 Announce Type: replace-cross Abstract: Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural net