AI research from July 2026

The paper demonstrates that using LoRA adapters can rewrite AI-generated text to match a specific user's writing style without needing explicit style instructions.

The paper introduces a method that uses grounded transformation chains to supervise intermediate reasoning steps for grid-based visual puzzles.

The authors introduce AgentHPOBench to evaluate how effectively LLM agents perform sequential hyperparameter optimization across thirty machine learning tasks.

The researchers demonstrate that robots can learn effective manipulation policies using only high-fidelity handheld video demonstrations instead of expensive real-robot teleoperation data.

OmniDelta optimizes token compression in audio-video large language models by dynamically allocating processing budgets based on task-specific relevance.

The paper introduces a stacked architecture for quantum algorithms that allows users to adjust the trade-off between the ease of training a model and its resistance to being simulated by classical computers.

ID-V2V is a generative framework that uses multi-stream control signals to restyle videos while maintaining strict subject identity and performance.

The paper demonstrates that using a three-stage multi-agent pipeline instead of a single model call significantly changes how models align with specific target objectives.

The researchers developed Diff-Logic, a method for running EEG classification on edge devices by replacing heavy floating-point arithmetic with sparse Boolean circuits.

VGOcc uses visual geometric features to improve 3D scene occupancy prediction from standard camera images.

The paper introduces the 3D-Fit benchmark to evaluate how effectively general-purpose LLMs navigate spatial constraints in molecular generation compared to specialized diffusion models.

Jina-reranker-v3.5 introduces a hybrid attention architecture and self-distillation protocol to improve retrieval performance across varied and semi-structured domains.

This paper confirms that the Ferraro result, which states that plasma angular velocity remains constant along magnetic field lines, holds true for rotating axisymmetric magnetic mirror machines at sonic or supersonic speeds.

The WorldCupArena benchmark assesses how effectively language models and autonomous agents predict complex outcomes for future football matches by combining pre-match data with web-based research.

The paper provides a design rule for aggregating agent data that prevents unstable learning in large cooperative multi-agent systems.

Researchers developed a layered defense strategy using access controls and workload monitoring to protect self-hosted AI agents from malicious self-state corruption.

The O-VAD system uses object-centric tracking and chain of thought reasoning to detect and explain anomalies in industrial video sequences.

EVOLVE is a neural volume compression framework that enables variable-rate encoding across diverse scientific datasets using a unified, optimized autoencoder architecture.

This paper analyzes the performance of Sample-based Quantum Diagonalization by testing how deployment choices like initialization, qubit mapping, and noise mitigation impact energy accuracy.

The paper introduces ATLAS, a procedure for uncovering invariant and transferable latent signals to improve predictive modeling across environments with varying feature distributions.