Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
Index Stats6,189 papers
ArXivCSExplorer

Understand any CS paper in 60 seconds — no login required

Hybrid search: keyword + semanticⓘ| Semantic-only search →

Try: LoRA fine-tuning·ZK-SNARKs·distributed consensus·Mamba SSM

All Features

Everything you need to explore, understand, and track CS research

📝

Abstract Search

Paste any paper text to find semantically similar work instantly

⚖️

Compare

Side-by-side diff of two papers — methods, results, claims

🌐

Explore

Browse the full indexed arXiv CS corpus

👤

Authors

Researcher profiles, timelines and co-author graphs

★

Bookmarks

Save and organise papers for later reading

🔬

Claim Tracker

Type any claim — see which papers support or contradict it

Achievements

View all
0papers
0day streak
0/0badges
First Steps0 / 1

Start reading papers to earn your first badge

Live RSS Feed

Subscribesee all →
cs.CR1d ago

From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs

This paper reveals a new vulnerability in Language Model (LLM) inference efficiency caused by persona consistency and proposes RolePlay, a framework to amplify inference costs.

Zhiyi Mou, Wangze Ni, Tianfang Xiao et al.

cs.CRcs.AI1d ago

Stemma: Induced Decision Regions Reveal LLM Provenance

This paper introduces Stemma, a black-box LLM fingerprinting method that abstracts away surface-form variation and measures the inheritance of decision regions for reliable provenance testing.

Keyu Zhang, Vadim Safronov, Andrew Martin

cs.CLcs.AI1d ago

Pass the Baton: Trajectory-Relayed On-Policy Distillation

The paper introduces Relay On-Policy Distillation (Relay-OPD), a method for on-policy distillation that constructs relay trajectories to address prefix failure and improve performance.

Haolei Xu, Xiaowen Xu, Haiwen Hong et al.

cs.AIcs.CV1d ago

Desktop-Delta Bench: Do Computer-Use Models Understand Desktop GUI Transitions?

This paper introduces Desktop-Delta Bench (DDB), an offline step-level benchmark for evaluating computer-use agents' ability to reconstruct causal transitions in desktop GUI environments.

Abhishek Pillai, Samir Kumar Nayak, Yuan Chen

Recommended for you

From your bookmarks →