Search: “models”

Modulating Cross-Modal Convergence with Single-Stimulus, Intra-Modal Dispersion

arXiv:2604.21836v1 Announce Type: cross Abstract: Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalitie

safetyarxiv-cs-ai

Nonlinear Causal Discovery through a Sequential Edge Orientation Approach

DGX agent

arXiv:2506.05590v3 Announce Type: replace-cross Abstract: Recent advances have established the identifiability of a directed acyclic graph (DAG) under additive noise models (ANMs), spurring the develo

applicationsarxiv-cs-lg

24 Apr 2026

Applications

On Reasoning Behind Next Occupation Recommendation

arXiv:2604.21204v1 Announce Type: cross Abstract: In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In thi

applicationsarxiv-cs-ai

PanGuide3D: Cohort-Robust Pancreas Tumor Segmentation via Probabilistic Pancreas Conditioning and a Transformer Bottleneck

arXiv:2604.20981v1 Announce Type: cross Abstract: Pancreatic tumor segmentation in contrast-enhanced computed tomography (CT) is clinically important yet technically challenging: lesions are often sma

researcharxiv-cs-cv

Applications

Promoting Simple Agents: Ensemble Methods for Event-Log Prediction

arXiv:2604.21629v1 Announce Type: cross Abstract: We compare lightweight automata-based models (n-grams) with neural architectures (LSTM, Transformer) for next-activity prediction in streaming event l

applicationsarxiv-cs-ai

Really impressed by how smooth switching most of my coding tasks to Codex (GPT-5.5) from Claude Code (Opus 4.7) has been. I thought it was g…

Really impressed by how smooth switching most of my coding tasks to Codex (GPT-5.5) from Claude Code (Opus 4.7) has been. I thought it was going to be more difficult and that I would be 'fighting' wit

model-releasesdair-ai--x

Agents

Sakana AI entered the commercial API market with the beta launch of 'Sakana Fugu,' a sophisticated multi-agent orchestration system previous…

Sakana AI entered the commercial API market with the beta launch of 'Sakana Fugu,' a sophisticated multi-agent orchestration system previously utilized as their internal secret weapon. Fugu fundamenta

agentsdavid-ha--x

Tutorials

Sapiens2

arXiv:2604.21681v1 Announce Type: new Abstract: We present Sapiens2, a model family of high-resolution transformers for human-centric vision focused on generalization, versatility, and high-fidelity o

tutorialsarxiv-cs-cv

SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors

arXiv:2511.18264v3 Announce Type: replace Abstract: Existing satellite video tracking methods often struggle with generalization, requiring scenario-specific training to achieve satisfactory performan

Local Ai

SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference

arXiv:2604.21231v1 Announce Type: cross Abstract: Efficient inference for on-device Large Language Models (LLMs) remains challenging due to limited hardware resources and the high cost of the prefill

local-aiarxiv-cs-ai

Spatial Metaphors for LLM Memory: A Critical Analysis of the MemPalace Architecture

model-releasesarxiv-cs-ai

arXiv:2604.21284v1 Announce Type: new Abstract: MemPalace is an open-source AI memory system that applies the ancient method of loci (memory palace) spatial metaphor to organize long-term memory for l

StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

arXiv:2604.21689v1 Announce Type: cross Abstract: Creative face stylization aims to render portraits in diverse visual idioms such as cartoons, sketches, and paintings while retaining recognizable ide

Temporal Taskification in Streaming Continual Learning: A Source of Evaluation Instability

model-releasesarxiv-cs-lg

arXiv:2604.21930v1 Announce Type: new Abstract: Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that

Transformer-Progressive Mamba Network for Lightweight Image Super-Resolution

arXiv:2511.03232v2 Announce Type: replace Abstract: Recently, Mamba-based super-resolution (SR) methods have demonstrated the ability to capture global receptive fields with linear complexity, address

researcharxiv-cs-cv

When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation

arXiv:2604.21309v1 Announce Type: new Abstract: Multi-document news summarisation systems are increasingly adopted for their convenience in processing vast daily news content, making fairness across d

Applications

WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images

arXiv:2604.21182v1 Announce Type: new Abstract: We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting

applicationsarxiv-cs-cv

Industry

5B tokens in ml-intern in 48h 😅😅😅

5B tokens in ml-intern in 48h 😅😅😅 we burned through 5 billion tokens in 48h. turns out giving everyone unlimited access to the most expensive model on the planet is not a great business strategy 🙈 So

industryclem-delangue--x

Adaptive Multi-task Learning for Multi-sector Portfolio Optimization

arXiv:2507.16433v2 Announce Type: replace-cross Abstract: Accurate transfer of information across multiple sectors to enhance model estimation is both significant and challenging in multi-sector portf

researcharxiv-cs-lg

Tools

[AINews] Tasteful Tokenmaxxing

This episode of AINews from Latent Space likely discusses strategies for optimizing token usage and efficiency in AI models, focusing on practical approaches to maximizing computational value while ma

toolslatent-space

Apple fixes a bug that stored notifications for deleted messages on iPhone and iPad, following a report that police used it to extract deleted Signal messages (Lorenzo Franceschi-Bicchierai/TechCrunch)

Lorenzo Franceschi-Bicchierai / TechCrunch: Apple fixes a bug that stored notifications for deleted messages on iPhone and iPad, following a report that police used it to extract deleted Signal messag

model-releasestechmeme

Benchmarking ResNet for Short-Term Hypoglycemia Classification with DiaData

arXiv:2511.02849v2 Announce Type: replace-cross Abstract: Individualized therapy is driven forward by medical data analysis, which provides insight into the patient's context. In particular, for Type

btw in talking to friends the best framing for how to discuss GPT-Image-2-Thinking taking multiple tens of mins for generation and being abl…

btw in talking to friends the best framing for how to discuss GPT-Image-2-Thinking taking multiple tens of mins for generation and being able to oneshot QR codes and diagrams and logos and foods and f

model-releasesswyx--x

Causal-Transformer with Adaptive Mutation-Locking for Early Prediction of Acute Kidney Injury

arXiv:2604.20259v1 Announce Type: new Abstract: Accurate early prediction of Acute Kidney Injury (AKI) is critical for timely clinical intervention. However, existing deep learning models struggle wit

researcharxiv-cs-lg

Claude Code spend had gotten to $10.95M runrate peak at SemiAnalysis But then Opus 4.7 saved me. More token effecient for tasks, smarter, an…

model-releasesdylan-patel--x

Claude Code spend had gotten to $10.95M runrate peak at SemiAnalysis But then Opus 4.7 saved me. More token effecient for tasks, smarter, and no fast mode. Thank you @AnthropicAI You saved me from ban

Commonsense Knowledge with Negation: A Resource to Enhance Negation Understanding

arXiv:2604.19921v1 Announce Type: new Abstract: Negation is a common and important semantic feature in natural language, yet Large Language Models (LLMs) struggle when negation is involved in natural

researcharxiv-cs-cl

Tutorials

Confidently wrong is worse than just wrong. When an AI searches one giant knowledge base for everything, it finds something—and serves it up…

Confidently wrong is worse than just wrong. When an AI searches one giant knowledge base for everything, it finds something—and serves it up like it's the answer. That's not a model problem. That's a

tutorialspinecone--x

Degrees, Levels, and Profiles of Contextuality

arXiv:2603.26692v3 Announce Type: replace-cross Abstract: We introduce a new notion, that of a contextuality profile of a system of random variables. Rather than characterizing a system's contextualit

DRIV-EX: Counterfactual Explanations for Driving LLMs

arXiv:2603.00696v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose

Dual Causal Inference: Integrating Backdoor Adjustment and Instrumental Variable Learning for Medical VQA

model-releasesarxiv-cs-ai

arXiv:2604.20306v1 Announce Type: cross Abstract: Medical Visual Question Answering (MedVQA) aims to generate clinically reliable answers conditioned on complex medical images and questions. However,

Enhancing Speaker Verification with Whispered Speech via Post-Processing

arXiv:2604.20229v1 Announce Type: cross Abstract: Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated spee

Agents

Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Po…

Evals ~= Environments…they’re one of the best investments a team can make for improving agents Step 0: Turn On Tracing for Agents Step 1: Point compute at Traces to understand agent behavior, segment

agentsharrison-chase--x

Fast Amortized Fitting of Scientific Signals Across Time and Ensembles via Transferable Neural Fields

arXiv:2604.19979v1 Announce Type: cross Abstract: Neural fields, also known as implicit neural representations (INRs), offer a powerful framework for modeling continuous geometry, but their effectiven

researcharxiv-cs-cv

Generalization and Membership Inference Attack a Practical Perspective

arXiv:2604.19936v1 Announce Type: cross Abstract: With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previ

Information Aggregation with AI Agents

arXiv:2604.20050v1 Announce Type: cross Abstract: Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing pr

ItemRAG: Item-Based Retrieval-Augmented Generation for LLM-Based Recommendation

arXiv:2511.15141v2 Announce Type: replace-cross Abstract: Recently, large language models (LLMs) have been widely used as recommender systems, owing to their reasoning capability and effectiveness in

IVY-FAKE: A Unified Explainable Framework and Benchmark for Image and Video AIGC Detection

model-releasesarxiv-cs-ai

arXiv:2506.00979v5 Announce Type: replace-cross Abstract: The rapid development of Artificial Intelligence Generated Content (AIGC) techniques has enabled the creation of high-quality synthetic conten

Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation

model-releasesarxiv-cs-cl

arXiv:2502.12911v3 Announce Type: replace Abstract: Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL ge

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation

arXiv:2601.14896v2 Announce Type: replace Abstract: Multilingual retrieval-augmented generation (MRAG) requires models to effectively acquire and integrate beneficial external knowledge from multiling

Location-Aware Pretraining for Medical Difference Visual Question Answering

arXiv:2603.04950v2 Announce Type: replace-cross Abstract: Differential medical VQA models compare multiple images to identify clinically meaningful changes and rely on vision encoders to capture fine-

Markov reads Pushkin, again: A statistical journey into the poetic world of Evgenij Onegin

arXiv:2604.20221v1 Announce Type: new Abstract: This study applies symbolic time series analysis and Markov modeling to explore the phonological structure of Evgenij Onegin-as captured through a graph

researcharxiv-cs-cl

Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy

arXiv:2601.02989v2 Announce Type: replace Abstract: Large language models (LLMs), despite strong performance on complex mathematical problems, exhibit systematic limitations in counting tasks. This is

researcharxiv-cs-cl

Memorization, Emergence, and Explaining Reversal Failures: A Controlled Study of Relational Semantics in LLMs

arXiv:2601.02931v2 Announce Type: replace Abstract: Autoregressive LLMs perform well on relational tasks that require linking entities via relational words (e.g., father/son, friend), but it is unclea

MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design

model-releasesarxiv-cs-lg

arXiv:2412.14590v2 Announce Type: replace Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions sti

MSLAU-Net: A Hybrid CNN-Transformer Network for Medical Image Segmentation

arXiv:2505.18823v2 Announce Type: replace Abstract: Accurate medical image segmentation allows for the precise delineation of anatomical structures and pathological regions, which is essential for tre

Agents

Neural Bandit Based Optimal LLM Selection for a Pipeline of Subtasks

arXiv:2508.09958v3 Announce Type: replace Abstract: As large language models (LLMs) become increasingly popular, there is a growing need to predict which out of a set of LLMs will yield a successful a

agentsarxiv-cs-cl

NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

arXiv:2602.15353v2 Announce Type: replace-cross Abstract: Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowled

safetyarxiv-cs-ai

New in the Codex app: - GPT-5.5 - Browser control - Sheets & Slides - Docs & PDFs - OS-wide dictation - Auto-review mode Enjoy!

model-releasessam-altman--x

The Codex app now includes several new features: GPT-5.5 integration, browser control capabilities, support for Google Sheets and Slides, document and PDF handling, OS-wide dictation functionality, an

OpenAI says GPT-5.5's improvements are strongest in agentic coding, computer use, and early scientific research, which require reasoning across longer contexts (Madison Mills/Axios)

Madison Mills / Axios: OpenAI says GPT-5.5's improvements are strongest in agentic coding, computer use, and early scientific research, which require reasoning across longer contexts — OpenAI on Thurs

model-releasestechmeme