AAAI 2026 Workshop AIR-FM Submissions

COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation
Kenji Sahay, Snigdha Pandya, Rohan Nagale, Anna Lin, Shikhar Shiromani, Kevin Zhu, Sunishchal Dev
- Published: 06 Nov 2025, Last Modified: 07 Dec 2025
- AIR-FM Poster
- Readers: Everyone
BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision Language Models
Sunny Gupta, Shounak Das, Amit Sethi
- Published: 06 Nov 2025, Last Modified: 24 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Prompt-Adaptive Quantization: Adaptive Per-Prompt Routing for Efficient LLM Inference
Gabriel Jimenez, Vivann Khanna, Rishi Sastri, Raine Ma, Soham Chatterjee, Kevin Zhu, Sunishchal Dev
- Published: 06 Nov 2025, Last Modified: 11 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles
Wang Ma, Debarun Bhattacharjya, Junkyu Lee, Nhan H Pham, Harsha Kokel, Qiang Ji
- Published: 06 Nov 2025, Last Modified: 10 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Future Is Unevenly Distributed: Forecasting Ability Of LLMs Depends On What We’re Asking
Chinmay Karkar, Paras Chopra
- Published: 06 Nov 2025, Last Modified: 10 Dec 2025
- AIR-FM Oral
- Readers: Everyone
Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls
Ora Nova Fandina, Eitan Farchi, Shmulik Froimovich, Raviv Gal, Wesam Ibraheem, Rami Katan, Alice Podolsky
- Published: 06 Nov 2025, Last Modified: 15 Jan 2026
- AIR-FM Poster
- Readers: Everyone
Next-Frame Prediction as a Reliability-Aware Training Paradigm for Robust Vision Encoders
Marcel Simon, Eunbin Lee, Tae-Ho Kim, Seul-Ki Yeom
- Published: 06 Nov 2025, Last Modified: 03 Dec 2025
- AIR-FM Oral
- Readers: Everyone
Know Or Not: a library for systematically evaluating out-of-knowledge base robustness
Jessica Foo, Pradyumna Shyama Prasad, Shaun Khoo
- Published: 06 Nov 2025, Last Modified: 09 Dec 2025
- AIR-FM Poster
- Readers: Everyone
LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
Elliot L Epstein, John Winnicki, Thanawat Sornwanee, Rajat Vadiraj Dwaraknath
- Published: 06 Nov 2025, Last Modified: 11 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis
Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan, Kevin Zhu, Parham Sharafoleslami, Maheep Chaudhary
- Published: 06 Nov 2025, Last Modified: 06 Nov 2025
- AIR-FM Poster
- Readers: Everyone
Reasoning Models are Test Exploiters: Rethinking Multiple Choice
Narun Krishnamurthi Raman, Taylor Lundy, Kevin Leyton-Brown
- Published: 06 Nov 2025, Last Modified: 08 Dec 2025
- AIR-FM Poster
- Readers: Everyone
BLUFF-1000: Measuring Uncertainty Expression in RAG
Ron Zharzhavsky, Emma Wong, Daniel Ketema
- Published: 06 Nov 2025, Last Modified: 06 Nov 2025
- AIR-FM Poster
- Readers: Everyone
SafeGen: Benchmarking Inference-Time Methods for Privacy-Preserving Text Generation
Aravilli Atchuta Ram
- Published: 06 Nov 2025, Last Modified: 11 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models
Madison Van Doren, Casey Ford
- Published: 06 Nov 2025, Last Modified: 25 Nov 2025
- AIR-FM Poster
- Readers: Everyone
Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models
Benjamin Yu, Ziyang Liu, Justin Cui
- Published: 06 Nov 2025, Last Modified: 11 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Beyond Grey-Box Assumptions: Uncertainty-Guided Example Selection for Black-Box Language Models
Egor Krasheninnikov, Zainab Afolabi, Giuseppe Mascellaro
- Published: 06 Nov 2025, Last Modified: 11 Dec 2025
- AIR-FM Poster
- Readers: Everyone
VISOR: Visual Input based Steering for Output Redirection in Large Vision Language Models
Mansi Phute, Ravikumar Balakrishnan
- Published: 06 Nov 2025, Last Modified: 01 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Can In-Context Learning Defend against Backdoor Attacks to LLMs
Yonghua Zhu, Qiqi Tao, Na Zhao
- Published: 06 Nov 2025, Last Modified: 10 Dec 2025
- AIR-FM Poster
- Readers: Everyone
AlignVQA: Debate-Driven Multi-Agent Calibration for Vision Language Models
Ayush Pandey, Jai Bardhan, Ramya S Hebbalaguppe
- Published: 06 Nov 2025, Last Modified: 10 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Quantifying Conversational Reliability of Large Language Models under Multi-Turn Interaction
Jiyoon Myung
- Published: 06 Nov 2025, Last Modified: 30 Nov 2025
- AIR-FM Poster
- Readers: Everyone
Task Interference in VLMs for Autonomous Driving: When Better Perception Hurts Planning
Sai Bhargav Rongali, Aadya Pipersenia, Kenji Okuma
- Published: 06 Nov 2025, Last Modified: 04 Dec 2025
- AIR-FM Poster
- Readers: Everyone
Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models
Rohit Kumar Salla, Manoj Saravanan, Shrikar Reddy Kota
- Published: 06 Nov 2025, Last Modified: 09 Dec 2025
- AIR-FM Poster
- Readers: Everyone