AI Research Paper Feed

TLDR: ILRec improves LLM-based recommendation systems by using self-hard negatives from intermediate layers for better preference learning.

TLDR: ReIn is a method for conversational agents to recover from errors by integrating an external reasoning module without altering the model's parameters or prompts.

TLDR: The paper introduces 'fail-closed alignment' for large language models to enhance safety by ensuring refusal mechanisms remain effective even if part of the system is compromised.

TLDR: This study audits how large language models (LLMs) associate personal data with individuals, revealing the models' ability to accurately generate personal information and raising privacy concerns.

TLDR: JEPA-DNA is a new framework for genomic foundation models that improves understanding of genomic sequences by integrating high-level functional embeddings with traditional generative objectives.

TLDR: M2F is a framework that automates the formalization of entire mathematical textbooks into Lean code, achieving high proof success rates and significantly reducing the time needed compared to manual efforts.

TLDR: MeGU is a new framework for machine unlearning that uses multi-modal large language models to selectively erase target data influence while preserving model utility.

TLDR: The Arcee Trinity Large is a 400B parameter sparse model using a novel MoE approach, with successful training on 17 trillion tokens and new load balancing strategies.

TLDR: This study examines how AI coding agents' pull request descriptions differ and how these differences affect human reviewers' responses and merge outcomes on GitHub.

TLDR: HQFS is a hybrid quantum-classical system that improves financial forecasting and optimization by integrating quantum computing techniques, resulting in better prediction accuracy and decision-making efficiency.

TLDR: ALPS is a diagnostic challenge set designed to test deep semantic and pragmatic understanding in Arabic, revealing current model limitations in morpho-syntactic dependencies despite high fluency scores.

TLDR: This paper presents a novel approach to crystal structure prediction using large language models and constrained optimization to improve symmetry inference and enforce physical validity, achieving state-of-the-art results without relying on existing databases.

TLDR: The Quantum Scrambling Born Machine uses fixed entangling unitaries and optimized single-qubit rotations to effectively model probability distributions, demonstrating competitive performance with classical models.

TLDR: FLoRG improves federated fine-tuning of large language models by using a single low-rank matrix and Procrustes alignment, enhancing accuracy and reducing communication overhead.

TLDR: The study introduces a generative model using Wasserstein Autoencoders to efficiently explore laser pulse shapes in photoinjectors, reducing reliance on costly simulations.

TLDR: IRIS is a cost-effective, learning-driven robotic camera system for cinematic motion control, using imitation learning to achieve smooth and repeatable camera movements.

TLDR: The Multi-Probe Zero Collision Hash (MPZCH) effectively prevents embedding collisions in large-scale recommendation systems, improving model freshness and performance.

TLDR: The paper introduces an adaptive decentralized optimization method using three-operator splitting and local stepsize adjustments, achieving robust convergence for convex and strongly convex problems.

TLDR: The paper presents a unified framework for addressing locality in scalable multi-agent reinforcement learning (MARL) by introducing a policy-dependent approach to the exponential decay property (EDP) of value functions.

TLDR: The paper introduces 'Wink', a system that automatically corrects misbehaviors in autonomous coding agents, significantly improving their performance and reducing the need for manual intervention.