All Articles
17800 articles total
Some Simple Economics of AGI
A discussion regarding the economic implications and theorized outcomes of Artificial General Intelligence (AGI).
A glitch in February of the year 0
A discussion about a chronological glitch occurring in the year 0 during the month of February.
AI-Driven Synthesis for High-Tech System Design: Automating Innovation
Introduces computational design synthesis (CDS) using generative AI to automate high-tech system design and reduce human supervision.
Tandem Reinforcement Learning with Verifiable Rewards
Proposes Tandem Reinforcement Learning (TRL) to improve the legibility and compatibility of LLM reasoning chains between senior and junior agents.
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Presents the Agent-Native Immune System (ANIS), a biologically inspired runtime defense architecture to protect autonomous agents from hijacking and poisoning.
DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers
Introduces DataStates-LLM, a checkpointing architecture that decouples state abstraction from data movement to accelerate extreme-scale LLM training.
Position: The Term "Machine Unlearning" Is Overused in LLMs
A position paper arguing that the term 'machine unlearning' is overused and should be strictly reserved for dataset-defined deletion.
OverFlowLight: Real-Time Gridlock Prevention and Traffic Signal Optimization for Urban Intersections
Presents OverFlowLight, a real-time framework using multi-modal sensing and RL to prevent urban traffic gridlock by dynamically inserting overflow phases.
CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models
Introduces CalBrief, a diagnostic benchmark for evaluating how well LLMs calibrate scientific takeaways based on the strength of provided evidence.
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
Proposes the Agentic Publication Protocol (APP), a repository format that bundles papers with executable code and instructions for agent-based reproduction.
HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88
HackerRank has open-sourced its Applicant Tracking System (ATS), leading to discussions about how resumes are scored by automated systems.
Understanding Rollout Error in Graph World Models
Researchers propose Error-Aware Graph World Models (GWMs) to reduce rollout error and planning regret in environments represented as graphs.
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
The Grounded Iterative Language Planning (GILP) framework combines parameterized world models with LLM reasoning to significantly reduce hallucinations in agents.
ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents
ATOD is a new hybrid distillation algorithm that blends on-policy distillation and RL to improve the training of small language-model agents for long-horizon tasks.
NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning
The NormAct benchmark evaluates whether embodied AI agents can comply with hidden social norms, introducing NormPerceptor to help agents detect such norms.
Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing
SD-GPS is a solver-driven framework for geometry problem solving that uses a symbolic solver as an execution oracle to improve autoformalization and theorem proposing.
RelBall: Relation Ball with Quaternion Rotation for Knowledge Graph Completion
RelBall is introduced as a Knowledge Graph Completion model using quaternion rotations and modulus transformations to better handle complex relational patterns and hierarchies.
Lifted Causal Inference
The paper introduces Lifted Causal Inference (LCI) using parametric causal factor graphs to efficiently compute causal effects in relational domains.
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
JD.com details Oxygen AIIC, an industrial-scale LLM/VLM-centric platform for managing item knowledge across billions of SKUs.
Ontology-Guided Evidence Path Inference for Multi-hop Knowledge Graph Question Answering
The OPI framework uses ontology-guided evidence path inference to reduce the search space and improve accuracy in multi-hop knowledge graph question answering.