Lattice AI Research

Research focus

Reasoning & Chain-of-Thought (2)Eval Frameworks & Benchmarks (1)Interpretability & Mechanistic Interp (1)Code Generation & Program Synthesis (1)Natural Language Processing (1)

Frequent co-authors

Quang H. Nguyen (1)Hung T. Q. Le (1)Hung Le (1)Xiusi Chen (1)

Papers (2)

Mar 17, 2026

H. Phan +6Mar 17, 2026

Decoding the Critique Mechanism in Large Reasoning Models

LRMs can often correct themselves even after making mistakes in their reasoning, hinting at a powerful, untapped "hidden critique ability" that can be unlocked with targeted interventions in the latent space.

H. Phan, Quang H. Nguyen, Hung T. Q. Le +4

Eval Frameworks & Benchmarks Interpretability & Mechanistic Interp Reasoning & Chain-of-Thought

Feb 24, 2026

Cuong Chi Le +10Feb 24, 2026

SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference

LLMs can generate more accurate and complete postconditions by engaging in iterative refinement guided by correctness feedback, rather than relying on single-pass prompting.

Cuong Chi Le, Minh V. T Pham, Minh V. T. Pham +8

Code Generation & Program Synthesis Natural Language Processing Reasoning & Chain-of-Thought

Search

H. Phan

Research focus

Frequent co-authors

Papers (2)