All notes, newest first
2,343 notes. Notes 2,301 to 2,343, page 47 of 47.
GIF: Locally Sound Geometric Information Flow Control for LLMs
Researchers present a new framework called Geometric Information Flow (GIF) for tracking information flow from input tokens to outputs in large language models. This framework uses the Jacobian and local output…
GIF: Locally Sound Geometric Information Flow Control for LLMs
Researchers have proposed a new method called Geometric Information Flow (GIF) for controlling information flow in large language models used in agentic systems. GIF uses the model's Jacobian and local output geometry…
GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation
The paper presents a method called GRINQH (GRaded INput-based Quantization Hierarchy) to accelerate the decoding process of language models during inference, particularly beneficial for edge-computing settings. The…
HOLMES: Evaluating Higher-Order Logical Reasoning in LLMs
The paper introduces HOLMES, a new benchmark for evaluating higher-order symbolic reasoning in Large Language Models (LLMs). This benchmark is designed to test the models' ability to reason over rules, predicates…
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
Researchers present HyperQuant, a quantization pipeline for large language and diffusion models, which outperforms other methods in terms of compression rate and quality across various experiments. The method combines…
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
The paper presents Kamera, a unified position-invariant multimodal KV cache that allows for training-free reuse of cached data in a way that avoids the need to recompute every look-back from scratch. The proposed…
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
Researchers propose a new method called Kamera for efficient use of KV cache by multimodal agents during reasoning iterations. The method avoids the need to re-encode from scratch and reduces the need for multiple…
Learning Process Rewards via Success Visitation Matching for Efficient RL
Researchers propose a method to make reinforcement learning (RL) more effective when dealing with sparse rewards, which are typically given only when a task is completed. The method incentivizes the RL-learned policy…
Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems
The paper presents Litmus, a system that creates evaluation metrics for AI pipelines by understanding the purpose of the code and asking questions about it. It was tested on three real AI pipelines and outperformed…
Litmus: Zero-Label, Code-Driven Metric Specification for Evaluating AI Systems
The paper introduces Litmus, a system that generates evaluation metrics for AI pipelines by understanding the intent from source code and targeted questions. The system was tested on three real-world AI pipelines and…
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
The authors present TF-RefusalBench, a multilingual benchmark for assessing over-alignment in legal language models used by the Swiss Federal Supreme Court. They find that over-alignment is complex and influenced by…
Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory
The study identifies a new phenomenon called Memory Contagion, where biased evaluators' influence can affect the experiences of language model agents, causing their memories to become biased as well. This bias is…
MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations
The researchers introduce a new benchmark called MuPPET to measure contextual privacy in multi-party conversations involving LLM agents handling sensitive personal data for multiple users. They found that models leak…
How Telcos Build Autonomous Networks with Agentic AI
NVIDIA describes how telecommunications companies are implementing agentic AI across network operations and customer workflows to build autonomous network management systems.
Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?
The authors question if AdamW, a commonly used optimizer for training large language models, is effective under heavy-tailed noise as its theory only applies to finite-variance regimes. They mention that sign-based…
POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation
Researchers have developed POTracker, an optimized large language model (LLM) for generating power outage reports that follow strict formatting and structural rules required by energy-sector regulatory bodies in the…
PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support
The study proposes a new framework called PsyBridge, designed to improve mental health assessment by integrating multiple dimensions, including clinically validated screening tools, cognitive evaluation, and…
PsyBridge: A Hybrid Intelligent Framework for Multi-Dimensional Mental Health Assessment and Decision Support
The study introduces PsyBridge, a hybrid intelligent framework aimed at improving the multi-dimensional assessment of mental health by integrating clinically validated screening tools, cognitive evaluations, and…
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
The paper introduces ReasoningLens, an open-source framework designed to address the transparency issue in Large Reasoning Models by creating hierarchical visualizations and diagnostic auditing tools for complex…
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
The paper introduces ReasoningLens, an open-source framework designed to help with the visualization and diagnostic auditing of complex reasoning chains in large reasoning models. The tool aims to address the issue of…
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
The paper proposes a new approach for training Vision-Language-Action (VLA) models through active, continual learning. This method aims to address the inefficiencies of traditional passive imitation learning by…
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
The paper introduces RS-Gen, a multi-stage image agent framework that aims to improve the performance of existing image generation and editing models by introducing a 'Questioning-and-Solving' closed-loop mechanism for…
Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
The authors propose a method for scaling Linear Mode Connectivity (LMC) to allow the merging of billion-parameter pretrained transformers, improving interpolation performance. The approach involves optimizing weight…
Semantic Browsing: Controllable Diversity for Image Generation
Researchers have developed a new method for generating diverse images using text-to-image models. Instead of relying on stochastic variations within the model, they induce diversity directly at the text level. The…
Semantic Browsing: Controllable Diversity for Image Generation
Researchers have developed a new approach for generating diverse images by controlling the diversity at the text level instead of relying on stochastic variation within the text-to-image model. This method allows users…
SPIRAL: Learning to Search and Aggregate
Researchers introduced SPIRAL, a framework for improving language model reasoning at test time. The framework uses three primitives - sequential reasoning within a trace, independently sampled parallel traces, and…
Teaching LLMs String Matching, Backtracking, and Error Recovery to Deduce Bases and Truth Tables for the Combinatorially Exploding Bit Manipulation Puzzles
The paper presents a new approach to solve the NVIDIA Nemotron Model Reasoning Challenge's Bit Manipulation Puzzles, where the goal is to discover hidden rules for transforming binary strings. The approach avoids…
UnBias-Plus: Detect, Explain, and Rewrite Bias
UnBias-Plus is a new open-source toolkit that aims to address the issue of bias in natural language content across various domains like journalism, education, and AI research. The toolkit offers four key features…
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
The paper introduces VeriEvol, a framework that addresses scaling issues in reinforcement learning for visual mathematical reasoning. The framework decouples the difficulty of prompts and the reliability of answers…
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct
The paper presents VeriEvol, a framework for scaling reinforcement learning in visual mathematical reasoning. It addresses the challenge of maintaining reliable reward labels as data volume grows by treating scaling as…
VideoAgent: All-in-One Framework for Video Understanding and Editing
Researchers have developed a new framework called VideoAgent to automate video editing tasks. The system can handle diverse editing operations and understand long videos, addressing limitations in existing automated…
MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop
Researchers have developed a new benchmark for AI agents on macOS desktops called MacAgentBench. The benchmark includes 676 tasks across 25 applications and measures the performance of various models using a…
PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement
The paper introduces PAPERCLAW, a multi-agent system that automates the research process from start to finish. It uses a large language model as its core, which can drive the entire pipeline and also allows for human…
Introducing Web Search on Amazon Bedrock AgentCore
AWS announced general availability of web search capabilities for Bedrock agents, with simplified integration for agent tool use.
Temporary Cloudflare Accounts for AI Agents
Cloudflare launched Temporary Accounts on Workers, allowing AI agents to deploy a live Worker in seconds via wrangler deploy --temporary. This enables ephemeral compute resources for agents without requiring persistent…
Amazon Bedrock AgentCore Harness Is Now Generally Available
AWS announced general availability of Amazon Bedrock AgentCore Harness, enabling simplified production-grade agent creation from minimal code. The announcement claims agents can be deployed "from idea to…
Project Fetch: Phase Two
Anthropic's Frontier Red Team ran a follow-up to their August 2025 "Project Fetch" robotics experiment. Using Claude Opus 4.7 with adaptive thinking (maximum effort) and Claude Code, they measured how fast the model…
Project Fetch: Phase Two
A follow-up to "Project Fetch" (August 2025) in which Anthropic's Frontier Red Team ran Claude Opus 4.7 autonomously on the same robotics tasks previously assigned to human-AI hybrid teams. The model completed those…
Bringing More Agent Harnesses and Frameworks to Cloudflare, Starting with Flue
Cloudflare opened its Agents SDK primitives to third-party frameworks, with Flue as the first framework integrated. Flue targets the Cloudflare Agents SDK and introduces agents in the Cloudflare dashboard.
Building an Open Ecosystem for AI Governance with Unity AI Gateway
Databricks introduced Unity AI Gateway, a governance infrastructure layer for AI deployment designed to support responsible AI deployment across organizations. It is framed as an "open ecosystem" for AI governance.
Agentic Coding and Persistent Returns to Expertise
Anthropic analyzed ~400,000 Claude Code sessions (Oct 2025–Apr 2026) to study how expertise and occupation shape agentic coding outcomes. The main finding: domain expertise — not coding background — predicts success…
Introducing Genie One, Genie Agents, and Genie Ontology
Databricks announced Genie One (enterprise-context-aware AI assistant), Genie Agents (agentic extensions), and Genie Ontology, framing the system as a "data-intelligent colleague" for enterprise data workflows.
From Pixels to Planning: Earth AI for Nature Restoration
Google Research describes applying "Earth AI" technology to environmental restoration: using satellite imagery analysis and AI-powered planning to support nature restoration efforts.
Page 47 of 47
