Tagged articles

HKUST

2 articles · Page 1 of 1

Sep 26, 2026 · Artificial Intelligence

Right Answer, Wrong Reason: LexAgentHallu Benchmarks Hidden Hallucinations in Legal AI Agents

HKUST researchers introduce LexAgentHallu, a hierarchical benchmark that evaluates hallucinations in legal AI agents by tracing entire reasoning trajectories, revealing that even top-performing systems exhibit hallucinations in 89% of execution traces and 68% of correct answers contain flawed reasoning.

Agent EvaluationHKUSTHallucination Detection

0 likes · 14 min read

Right Answer, Wrong Reason: LexAgentHallu Benchmarks Hidden Hallucinations in Legal AI Agents

HyperAI Super Neural

Jun 17, 2026 · Artificial Intelligence

Deterministic Video Depth (DVD): Open‑Source Framework Achieves Zero‑Shot SOTA

The DVD framework converts a pretrained video diffusion model into a deterministic, single‑pass video depth estimator, eliminating random sampling artifacts, preserving geometric and semantic priors, and reaching zero‑shot state‑of‑the‑art performance with 163× less training data.

Generative ModelsHKUSTZero-shot Learning

0 likes · 5 min read

Deterministic Video Depth (DVD): Open‑Source Framework Achieves Zero‑Shot SOTA