Research Feed Page 47

Search source-linked summaries of recent AI and machine-learning papers by topic, by date, or by whether they include code or a diagram.

Filter papers All papers

Browse by date

Resource filters

Sort options

Research results

Reinforcement Learning / Robotics By Slava Andrejev 2026-07-15
Lyapunov Exponent as Physics-Informed Dense Reward: RL Discovery of Stabilization Beyond the Kapitza Pendulum

The paper uses the Lyapunov characteristic exponent as a reward signal to teach reinforcement learning agents how to stabilize an inverted pendulum with vertical motion.

Efficiency & Inference / Benchmarks & Evals By Daniel Grillmeyer 2026-07-15
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study

The researchers introduced Cluster-based Sequential Feature Selection (CSFS), a wrapper method that reduces the computational cost of feature selection in renewable energy prediction pipelines.

Multimodal / Computer Vision By Zhihao Xie 2026-07-15
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders

VideoRAE replaces pixel-focused autoencoders with a system that maps video foundation model features into more efficient and semantically aware latent representations.

Agents / Safety & Alignment By Sanket Badhe 2026-07-15
Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

The researchers developed a security framework to protect the lifecycle of reusable LLM agent skills from creation through execution.

Agents / Reinforcement Learning By Leitian Tao 2026-07-15
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents

The researchers developed a method to assign rewards to intermediate steps in agent interactions to improve performance on long-horizon tasks.

Agents / Benchmarks & Evals By Wenxiao Wang 2026-07-15
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0

The paper introduces RELAI-VCL, a regression-aware optimizer that prevents agent performance from dropping when learning new tasks.

Safety & Alignment / Benchmarks & Evals By Mohammad Allahbakhsh 2026-07-15
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

This paper proposes a new method for penetration testing AI-enabled systems that focuses on violating operational objectives through AI-governed behavior rather than just compromising resources.

Reinforcement Learning / Efficiency & Inference By Mustafa Emre Gürsoy 2026-07-15
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points

The paper introduces Lighthouse RL, a reinforcement learning method that uses strategic reset points to improve sample efficiency in analog circuit sizing.

Training & Fine-Tuning By Katie Everett 2026-07-15
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth

The paper identifies how architecture choices like normalization placement and width expansion prevent gradient rank collapse in deep Transformer models at initialization.

Agents / Benchmarks & Evals By Maliha Noushin Raida 2026-07-15
Early Adoption of Agentic Coding Tools by GitHub Projects

The paper examines how developers integrate agentic coding tools into their workflows by analyzing pull request patterns across 2,361 GitHub repositories.

Computer Vision / Efficiency & Inference By Zhan Chen 2026-07-15
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study

The authors implement a domain routing system that dispatches page images to specialized OCR models, enabling accurate text extraction across varied historical Manchu writing styles.

Agents / Training & Fine-Tuning By Tianyi Zhou 2026-06-01
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

The paper introduces COLLEAGUE.SKILL, an end-to-end workflow that distills heterogeneous traces of person-grounded knowledge into inspectable, correctable, and agent-usable skills.

Agents / Efficiency & Inference By Alireza Salemi 2026-06-01
GrepSeek: Training Search Agents for Direct Corpus Interaction

GrepSeek replaces traditional vector-based search indices with an agent that interacts directly with raw corpus files using shell commands.

Training & Fine-Tuning / Reasoning By Daniil Plyusov 2026-06-01
Trust-Region Behavior Blending for On-Policy Distillation

The paper introduces a method called Trust Region Behavior Blending to stabilize on-policy distillation by controlling how teachers supervise student models during early training.