All Articles
17939 articles total
Show HN: Continuous Nvidia CUDA PC Sampling Profiler
A new continuous sampling profiler specifically designed for Nvidia CUDA GPUs to assist developers in identifying performance bottlenecks.
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
UltraQuant introduces a 4-bit KV caching mechanism for context-heavy AI agents, significantly improving time-to-first-token and output throughput on AMD GPUs.
Optimal Order of Multi-Agent and General Many-Body Systems
A research paper proposing a general framework for analyzing multi-agent systems, focusing on the balance between collective productivity and systemic fragility.
Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems
Introduces Contagion Networks, a framework for measuring how evaluation biases propagate through multi-agent LLM systems, and suggests using committees to mitigate this.
Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
Analysis of LLMs' ability to detect vulnerabilities in systems software, concluding that fine-tuning often results in 'calibration without comprehension' rather than actual security reasoning.
FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining
FreeStyle is a dual-reference generation framework that uses community LoRA mining to synthesize images while preserving content structure and separating style.
Efficient and Sound Probabilistic Verification for AI Agents
A new framework for sound and efficient probabilistic verification of AI agents using distributionally robust optimization to ensure security policy bounds.
Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in Agentic Control Planes
Introduces the Sovereign Execution Broker (SEB), a runtime enforcement boundary that separates proposal, admission, and execution to secure agentic control planes.
John Jumper leaves Google to join Anthropic
John Jumper, a key figure in AlphaFold, leaves Google to join Anthropic.
Court Records Should Be Free
A discussion on the necessity of making court records freely available to the public.
Robust $Q$-learning for mean-field control under Wasserstein uncertainty in common noise
Researchers present a robust Q-learning algorithm for mean-field control problems under Wasserstein uncertainty in common noise.
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
AutoPass is a multi-agent LLM framework that optimizes compiler performance tuning by analyzing internal compiler states and runtime feedback.
CRAX: Fast Safe Reinforcement Learning Benchmarking
CRAX is a fast, safe reinforcement learning benchmark utilizing the MuJoCo XLA (MJX) physics engine for hardware-accelerated 3D dynamics.
DataMagic: Transforming Tabular Data into Data Insight Video
DataMagic is an interactive system that uses a multi-agent architecture to transform raw tabular data into narrative data-insight videos.
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
NRT-Bench is a multi-turn red-teaming benchmark for LLM agents operating safety-critical systems, simulated via a nuclear power plant control room.
Multi-View Decompilation for LLM-Based Malware Classification
Research shows that using multiple decompiler views (e.g., Ghidra and RetDec) improves LLM-based malware classification and triage.
Repurposing a Speech Classifier for Guided Diffusion-Based Speech Generation
A study on repurposing a frozen speech classifier as the backbone for diffusion-based speech generation to reduce memory and computational costs.
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
The paper introduces CMPE, a lightweight conversational misdirection method to defend agentic AI systems against automated jailbreak attacks.
Music generation using Algebra, presented as web MIDI shop
A project demonstrating music generation using algebraic principles, presented as an interactive web-based MIDI shop.
FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching
Introduction of FlowMaps, a latent flow matching model that predicts future locations of dynamic objects in 3D spaces to improve robotic navigation.