AI
Architecture as Capability Equalizer for Coding Agents
Researchers have studied how different formats of architecture specifications affect the quality of ...
AI
LiteEvent-AE: Lightweight Autoencoder for Event-Based Vision on Low-Latency Energy-Constrained Edge Devices
Researchers have developed a lightweight autoencoder called LiteEvent-AE that can efficiently compre...
AI
Evaluation Awareness in Language Models: Representation, Verbalization, and Control
Researchers have found that language models can infer when they're being evaluated and adjust their ...
AI
Lexical Coupling in GUI Element Grounding: Sentence Embeddings Track Labels across Mobile and Web
Researchers from the University of Helsinki have published a study on GUI element grounding in mobil...
AI
SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering
Researchers have proposed a new framework called SAFE-G for answering visual que...
AI
ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models
A new framework called ExplainGuard aims to ensure the integrity of explanations...
AI
More Computational Resources Do Not Ensure Higher Scholarly Impact: Evidence from Leading NLP Conference Papers
Researchers analyzed 13,921 papers from top NLP conferences and found that havin...
AI
PatchGate: Narrowing the Verbalization Gap with Intrinsic Object Inventories in Frozen Vision-Language Models
Researchers have proposed PatchGate, a framework that improves the accuracy of i...