10
A First-Principles Theory of Slow Thinking and Active Perception
This paper provides a mathematical formulation of slow thinking and active perception to guide the design and training of reasoning-focused language models.
10
Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models
Researchers developed ScaleMOF, a dataset and fine-tuning strategy that enables large language models to predict and prioritize viable candidates for scaling up metal-organic framework syntheses.
10
PhasorFlow: A Python Library for Unit Circle Based Computing
PhasorFlow is a new open-source Python library designed to facilitate complex-valued computations on the unit circle manifold.
10
Theoria: Rewrite-Acceptability Verification over Informal Reasoning States
Researchers have developed Theoria, a verification architecture that audits large language model outputs by rewriting solutions into typed state transitions to ensure correctness.
10
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
This paper proposes a stepwise reinforcement learning approach to prevent text and image modalities from diverging during complex, interleaved multimodal reasoning tasks.
10
LoKA: Low-precision Kernel Applications for Recommendation Models At Scale
The LoKA framework introduces low-precision FP8 kernels tailored to the numerical sensitivities and communication demands of large-scale recommendation models.
10
Agentic Neural Architecture Search
Researchers propose a framework that combines large language model generation with neural architecture search to automate the design of neural networks in open-ended spaces.
10
Infinity-Parser2 Technical Report
Researchers have introduced Infinity-Parser2, a multimodal document parsing model trained using a controllable data-synthesis pipeline and reinforcement learning.
10
Adaptive Generation of Bias-Eliciting Questions for LLMs
Researchers developed a method to adaptively generate bias-eliciting questions to better identify and evaluate inherent biases in large language models.
10
DrugGen 2: A disease-aware language model for enhancing drug discovery
Researchers have introduced DrugGen-2, a generative language model designed to design small molecules based on both target protein sequences and disease ontology.
10
Deployment-Time Memorization in Foundation-Model Agents
This research analyzes how deployment-time memory configurations in foundation-model agents affect personalization utility, data extraction risks, and deletion fidelity.
10
Dual-Difficulty Curriculum Learning for Direct Preference Optimization
Researchers introduced a two-dimensional curriculum learning framework that categorizes alignment difficulty by prompt complexity and pairwise distinguishability to optimize direct preference optimization.
10
DocMaster: A Hierarchical Structure-Aware System for Document Analysis
DocMaster is a document analysis system that preserves the hierarchical structure of complex files to improve retrieval and question-answering performance in large language models.
10
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
The WCog-VLA framework integrates semantic world forecasting and generative world evolution to enable proactive decision-making in end-to-end autonomous driving.
10
Open-ended Multi-agent Autocurricula via Visual Inspection of Policies with Multi-modal LLMs
This study introduces a method that uses multimodal language models to visually evaluate reinforcement learning agent behaviors to design more effective training curricula.
10
What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness
Probing the internal activations of forecasting language models reveals that their hidden representations contain more accurate and better-calibrated probability estimates than their generated text.
10
Design driven infrastructure automation
The article discusses the role of reconciliation in design-driven automation for data center infrastructure.
10
Sonatel deploys OneWeb ground station in Senegal
Telecommunications companies are expanding satellite ground station infrastructure in Senegal and Canada.
10
Sponsored: Making solar and storage work for AI-scale data centers
This sponsored article discusses the integration of solar energy and battery storage systems to meet the power demands of AI-scale data centers.
10
Market Cap Down 60%, Insta360 Announces Robot Ambition With CameraMan Concept
Insta360 has introduced CameraMan, a conceptual intelligent photography robot that integrates its AI chip, camera, and audio technologies.
10
Insta360 unveils vision for AI-powered Cameraman robot on 11th anniversary
Insta360 has announced its vision for CameraMan, an AI agent concept designed for autonomous filming and photography.
10
A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents
Researchers evaluated the reliability of Gemini models acting as audio judges to score full-duplex voice agent conversations directly from raw waveforms.
10
A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosis
AegisDx is a new clinical reasoning framework that coordinates multiple specialized language models to reduce diagnostic errors and verify medical reasoning.
10
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Researchers have developed AUTOPILOT-VQA, a benchmark designed to evaluate how well vision-language models can reason about safety-critical traffic incidents using dashcam footage.