Group 1

Reasoning-Aware Hallucination Detection in Large Language Models: Evidence, Localization, and Faithful Process Diagnosis

Fatemeh Hadizadeh, Mahsa Jalali, Mostafa Karbalaei, Fatemeh Shahhosseini, Mohammad Shirkhani, Danial Parnian

Group 2

Machine Unlearning for Large Language Models: A Survey of Benchmarks, Methods, and Open Problems

Alireza Aalaie, Parsa Sadeghi, Danial Parnian, Omid Ghahroodi, Nazanin Yousefi

Group 3

Survey on LLM-as-a-Judge Reliability: A Review of Recent Advances

Parsa Gholami, Aria Alyasin, Mohsen Shirazi, Omid Ghahroodi, Hossein Shahabadi, Danial Parnian

Group 4

Survey on Verifier-Guided Multi-Step Reasoning: A Review of Recent Advances

Ali Heydari, Mohammadjavad Mohammadi, Ali Ghanbarian, Radin Cheraghi, Sahand Akramipour, Danial Parnian

Group 5

Survey on Mechanistic Interpretability of Reasoning: A Review of Recent Advances

Narges Javid, Ali Karimi, Zeinab Ehyaei, Mohammad Mostafa Rostamkhani, Moein Salimi, Shaygan Adim

Group 6

Survey on Reward Hacking in LLM Alignment: Problem Characterizations and Mitigation Strategies

Maryam Tavasoli, Sahar Razzaghi, Zahra Azar, Radin Cheraghi, Moein Salimi, Danial Parnian

Group 7

From Visual Evidence to Reasoning: A Survey of Reasoning in Vision-Language Models

Mobina Poulaei, Amir Qeysarbeigi, Masih Shalchian, Omid Ghahroodi, Hanieh Sartipi, Shaygan Adim

Group 8

Survey on Uncertainty Self-Awareness in LLMs: A Review of Recent Advances

Farbod Azimmohseni, Amirhossein Tighkhorshid, Mahdi Mastani, Danial Parnian, Ali Najar, Shaygan Adim

Group 9

A Survey on Recursive Reasoning Models

Aref Mousavi, Nima Zare, Amir Hossein Movahedi, Mahshid Dehghani, Muhammad Shirkhani, Danial Parnian

Group 10

Survey on Implicit Reasoning in LLMs: Hidden Computation, Latent Thought, and Test-Time Reasoning Beyond Text

Mohammad Ebrahimian, Armin Geramirad, Taha Izadi, Mahshid Dehghani, Sahand Akramipour, Shaygan Adim

Group 11

Survey on Process Supervision for Multi-Step Reasoning: A Structured Review of Process Reward Models

Amir Malekhosseini, Mohammadmahdi Nouriborji, Nazanin Yousefi, Danial Parnian, Shaygan Adim

Group 12

Survey on Multi-Agent System's Auditing and Failure Cases: A Review of Recent Advances

Amirali Miri, Sajjad Vaezi, Amir Ehsan Esmaeili, Fatemeh Shahhosseini, Pouya Behzadifar, Shaygan Adim

Group 13

Survey on Compositionality in VLMs: A Review of Recent Advances

Rozhan Ahmadi, Mohammad Mohammad Beigi, Parham Moghaddasi, Mohammadmostafa Rostamkhani

Group 14

Diffusion Models for Text Generation: Foundations, Scaling, Reasoning, Multimodality, Test-Time Computation, and Trustworthiness

Nima Niroumand, Amirhosein Attari, Pooria Kazem, Pouya Behzadifar, Hanieh Sartipi, Shaygan Adim