ArXiv TLDR

Zihan Wang

8 papers ยท Latest:

The JWST early galaxy crisis resolved by a reionization degeneracy

This paper resolves the JWST early galaxy crisis by showing a reionization degeneracy allows standard ฮ›CDM to explain bright z>10 galaxies.

2605.03635
Machine Learning

Jailbroken Frontier Models Retain Their Capabilities

Advanced jailbreaks impose minimal capability degradation on frontier models, challenging assumptions about their safety.

2605.00267
Information Retrieval

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG

FES-RAG purifies multimodal retrieval by selecting specific fragments, not whole documents, improving MLLM generation and reducing noise.

2604.27600
Information Retrieval

Factorized Latent Reasoning for LLM-based Recommendation

This paper introduces Factorized Latent Reasoning (FLR), an LLM-based recommendation framework that disentangles user preferences into multiple factors.

2604.26760
Computer Vision

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

GLM-5V-Turbo is a new foundation model integrating multimodal perception natively for enhanced agent reasoning, planning, and tool use across diverse contexts.

2604.26752
Natural Language Processing

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG

MEG-RAG introduces a semantic-aware metric and reranking framework to improve multimodal evidence grounding in RAG systems, enhancing generation accuracy.

2604.24564
Cryptography & Security

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

This paper empirically studies black-box skill stealing from proprietary LLM agents, demonstrating easy extraction and highlighting overlooked copyright risks.

2604.21829
Computer Vision

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects

VEFX-Bench introduces a large-scale dataset, a specialized reward model, and a benchmark for evaluating AI-assisted video editing systems.

2604.16272

๐Ÿ“ฌ Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week โ€” summarized, scored, and delivered to your inbox every Monday.