Welcome to NIU AI

Stay Connected: Subscribe to receive notifications about upcoming seminars and new presentations.

Share a Talk or Presentation: Interested in giving a talk or presentation? Contact us at contact@niuai.org

Towards Continual Learning in LLMs: Retrieval, Reasoning, and Memory

Overview Speaker: Sagar Sharma Date: Friday, November 6, 2026, 2:30 PM Room: PM103 Large Language Models (LLMs) face significant challenges in continuously acquiring new information, preserving existing knowledge, and reasoning across multiple sources. Although traditional Retrieval-Augmented Generation (RAG) enables LLMs to access external knowledge, it remains limited in associative reasoning, knowledge integration, and long-term memory management. Recent advances in non-parametric continual learning have introduced promising approaches that combine advanced retrieval mechanisms, knowledge graph-based reasoning, and dynamic memory architectures. These methods aim to enable LLMs to establish meaningful connections across information, adapt to evolving knowledge, and maintain persistent, context-aware memory without requiring frequent model retraining. ...

November 6, 2026 · 1 min · Sagar Sharma

Protocol-Qualified Scientific Evidence for Trustworthy Cross-Paper Comparison

🎬 Video coming soon. The recording of this talk will be posted here. Overview Speaker: Harish Varma Siravuri Date: Friday, October 30, 2026, 2:30 PM Room: PM103 Scientific papers are being published far faster than anyone can curate them by hand. So researchers increasingly depend on automatically extracted results (leaderboards, knowledge graphs, and LLM-based extraction) to compare methods across papers. These records are hard to trust, for three reasons. An extractor may copy a value incorrectly. Two values that were extracted correctly may come from different experimental conditions, such as a test split versus a validation split. And a system may name a “winner” that the available evidence does not actually support. ...

October 30, 2026 · 2 min · Harish Varma Siravuri

AI for Spin? Quantum Information, Chemical Reactions, and Critical Materials

Overview Speaker: Dr. Tao Xu, Distinguished Professor, Department of Chemistry and Biochemistry, NIU Date: Friday, October 16, 2026, 3:30 PM Room: PM110 An electron carries mass, charge, and spin. Controlling charge gave us modern computing. Controlling spin may give us quantum information, smarter chemistry, and better ways to recover critical materials. Prof. Xu takes us across three frontiers: Quantum information: how a chemically tunable semiconductor enables spin–spin interactions, the basis of a newly funded DOE project on quantum coherence. Chemical reactions: how controlling spin can steer reactions, improving the conversion of CO₂ into useful chemicals using electricity. An open challenge for AI: rare-earth ions with nearly identical charge and size respond differently to magnetic environments. Could AI help design materials that separate elements conventional chemistry struggles to tell apart? Why This Talk This isn’t a talk about using an off-the-shelf model. It’s a direct invitation from an experimental lab looking for AI collaborators. The questions on the table are ones ML researchers care about: Can algorithms uncover hidden interactions from noisy experimental signals? Can they guide which experiment to run next? Can they do inverse design, finding a material for a desired function? If you’re looking for real scientific data, a new application area, or a thesis/project idea, this is a great chance to meet a potential collaborator. No chemistry or physics background is needed. ...

October 16, 2026 · 2 min · Tao Xu

The AI Scientist and Automated Peer Review

Overview Speaker: Md. Toyaha Rahman Ratul Date: Friday, October 2, 2026, 2:30 PM Room: PM103 The story in short: in 2024, Sakana AI introduced “The AI Scientist,” a system that tries to do the full research cycle by itself. It generates an idea, writes the code, runs the experiments, writes the paper, and even reviews it. In 2025, one paper fully generated by its second version passed peer review at an ICLR workshop, with scores of 6, 7, and 6, which was higher than about 55% of the human-written papers there. The team withdrew the paper before publication, as they had planned with the organizers. In 2026, the work was published in Nature. It has started a big discussion in the community about what AI can and cannot do in research. ...

October 2, 2026 · 2 min · Md. Toyaha Rahman Ratul

Adversarial Attack and Defense on Language Models

Overview Speaker: Ibrahim Al Azher Date: Friday, September 18, 2026, 2:30 PM Room: PM103 This session covers adversarial attacks on language models and the defenses against them, organized in three parts: attacks, defenses, and tool-based attack and defense. The reading list for each part is below. Relevant Materials Attack Universal and Transferable Adversarial Attacks on Aligned Language Models Improved Techniques for Optimization-Based Jailbreaking on Large Language Models Tree of Attacks: Jailbreaking Black-Box LLMs Automatically PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning FLASH: Focused Layer Attention Sink Hijacking Defense Safety Alignment Should Be Made More Than Just a Few Tokens Deep AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing Tool-Based Attack and Defense Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents Prompt Injection as Role Confusion LLMs Encode Harmfulness and Refusal Separately When Safety Speaks a Language: A Mechanistic Analysis of Safety–Language Identity Entanglement in LLMs Refusal in Language Models Is Mediated by a Single Direction Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs ASIDE: Architectural Separation of Instructions and Data in Language Models (ICLR 2026)

September 18, 2026 · 2 min · Ibrahim Al Azher

Recursive Self-Improvement (RSI) in AI

Overview Speaker: Lei Zhang Date: Friday, September 4, 2026, 2:30 PM Room: PM103 Recursive self-improvement is one of the more plausible candidates for the next big thing in AI, and the real technical pivot under most AGI-timeline arguments. The system applies itself to itself. The essential move is self-application, which is why you can’t discuss RSI without fixed points. But “fixed point” here is three different things: Kleene’s second recursion theorem The Y combinator x* = f(x*) They don’t substitute for each other, and conflating them flips conclusions. The talk separates the three, then uses that ruler on deep equilibrium models (DEQs), neural architecture search (NAS), self-referential weight matrices, and neural quines. ...

September 4, 2026 · 1 min · Lei Zhang

Deep Learning and Foundation Models for Earth and Planetary Sciencess

Download the presentation slides Overview On April 10, 2026, Jichao Fang, a Ph.D. candidate in the Department of Earth, Atmosphere and Environment at Northern Illinois University, presented his research on deep learning and foundation models for Earth and planetary sciences. Jichao is also a Master’s student in Computer Science and is expected to graduate this year. ...

April 10, 2026 · 2 min · Jichao Fang

Anatomy of an Autonomous AI Agent: Frame Frameworks to OS

Overview On March 27, 2025, Tanish Kumar, a PhD student in the Computer Science department at Northern Illinois University, delivered a presentation on Anatomy of an Autonomous AI Agent: From Frameworks to OS, a research area exploring the architectural transition from simple AI tools to integrated agent operating systems. As AI technology evolves, the industry faces a significant gap: while powerful frameworks exist, the challenge remains in how to effectively assemble and manage these components into a reliable system. In his talk, Kumar introduced OpenClaw, a local-first, open-source “Agent OS” designed to move beyond basic orchestration. He discussed the system’s core architecture, including its two-store memory model, lane-aware concurrency control, and the critical separation of the control plane and data plane to ensure security and reliability in production-grade AI agents.

March 27, 2026 · 1 min · Tanish

Direct Preference Optimization

Overview Download the presentation slides Today in our AI/ML seminar, we were pleased to have Maliha Zahan Chowdhury as the presenter. Maliha is a first-year PhD student in Dr. Zhishuai Guo’s research group. Her talk focused on Direct Preference Optimization (DPO), primarily based on the original 2023 DPO paper. Although the paper was published only three years ago, it has already been cited nearly 8,000 times, reflecting its significant impact on LLM alignment and optimization research. ...

February 27, 2026 · 1 min · Maliha Zahan Chowdhury

Integrate RL with LLM Agents

Download the presentation slides Overview and Motivation Presentation on integrating reinforcement learning concepts with LLM engines to improve performance Multiple approaches exist to enhance LLM performance: in-context learning, post-training (reinforcement learning), and fine-tuning Focus on efficiently integrating RL concepts with LLMs, particularly for multi-agent systems Covers differences between reinforcement learning on LLMs versus reinforcement learning on LLM agents Addresses RL implementation in HPC systems due to memory-intensive requirements Multi-Agent System Fundamentals Multi-agent systems consist of multiple LLMs, each with specific roles and functions State acts as history, compiling all previous agent turns, context, and evidence in multi-turn systems Communication Topologies ...

February 20, 2026 · 11 min · Ibrahim Al Azher