AI research from July 2026 Page 2

The paper adapts PCMCI+, a causal discovery framework originally designed for regularly sampled data, to work with irregularly sampled event streams by using time-aware pairing strategies.

StructGen improves multi-reference image generation by using a structured identifier-based system to map textual instructions to specific reference images.

Researchers evaluated four frontier LLMs as autonomous forecasting agents using the 2026 FIFA World Cup as a contamination-free benchmark for decision accuracy and self-knowledge.

The researchers developed a method to train neural networks with formal robustness guarantees against convolutional perturbations such as motion blur.

The researchers developed a method called Three-Body Scattering Modeling that allows for high-quality image generation in a single inference step by treating particles as interacting entities.

The paper introduces TPIPS, a text-prompted metric that allows developers to calculate image similarity based on specific visual attributes rather than using generic, aspect-agnostic scores.

DiFA improves image generation quality in diffusion models by using historical prediction data to correct errors during inference without needing additional model training or network passes.

FlashRT uses an agentic framework to automate the complex process of optimizing heterogeneous model pipelines for real-time performance.

SWE-Pruner Pro automatically prunes redundant tool outputs by analyzing internal model states to lower token costs and improve performance without external scoring models.

HOMIE is a multimodal framework that improves how AI models generate personalized videos featuring consistent humans and objects by integrating multimodal guidance and identity-specific embeddings.

FlowMimic generates synthetic video editing data in real time by applying temporal flow fields to existing image editing samples, removing the need for labor-intensive mask annotations.

PPL-Factory is a method that selects the most informative subset of training data to improve fine-tuning performance while reducing computational overhead.

The paper introduces a causal inference framework to improve how RAG systems select actions by treating vector search as a nearest neighbor matching process.

The paper introduces a method that replaces compressed global visual vectors with uncompressed patch tokens to improve robotic manipulation precision while maintaining high computational efficiency.

The paper introduces a diagnostic benchmark that evaluates how well AI models simulate classical mechanics through a three-stage reasoning process.

The paper introduces a synthetic data generation framework that enables training API-calling agents without needing fully operational backend environments.

MagicSelector improves agent tool retrieval in mobile environments by using counterfactual reasoning and progressive reranking to eliminate semantic mismatches.

RynnBrain 1.1 introduces a unified framework that improves robotic manipulation by grounding visual understanding in physical space across different robot hardware.

The paper introduces an LLM-as-a-Coach method that replaces traditional scalar rewards in reinforcement learning with rich experiential knowledge to train open-ended task models.

Researchers improved Assamese speech recognition by fine-tuning the Whisper model using a combined dataset of validated and crowd-sourced audio.