Research Feed Page 41

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.

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.