Accepted Papers

Posters

Paper ID (AAAI26_Identifier_Paper#) Paper Title Authors Poster ID
AAAI26_W15_2 Beyond Hallucinations: A Composite Score for Measuring Reliability in Open-Source Large Language Models Rohit Kumar Salla, Manoj Saravanan, Shrikar Reddy Kota WS68
AAAI26_W15_4 Task Interference in VLMs for Autonomous Driving: When Better Perception Hurts Planning Sai Bhargav Rongali, Aadya Pipersenia, Kenji Okuma WS69
AAAI26_W15_5 Quantifying Conversational Reliability of Large Language Models under Multi-Turn Interaction Jiyoon Myung WS70
AAAI26_W15_11 AlignVQA: Debate-Driven Multi-Agent Calibration for Vision Language Models Ayush Pandey, Jai Bardhan, Ramya S Hebbalaguppe WS71
AAAI26_W15_12 Can In-Context Learning Defend against Backdoor Attacks to LLMs Yonghua Zhu, Qiqi Tao, Na Zhao WS72
AAAI26_W15_13 VISOR: Visual Input based Steering for Output Redirection in Large Vision Language Models Mansi Phute, Ravikumar Balakrishnan WS73
AAAI26_W15_14 Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning Svetlana Churina, Chebrolu Niranjan, Kokil Jaidka WS74
AAAI26_W15_15 Beyond Grey-Box Assumptions: Uncertainty-Guided Example Selection for Black-Box Language Models Egor Krasheninnikov, Zainab Afolabi, Giuseppe Mascellaro WS75
AAAI26_W15_16 Smart-GRPO: Smartly Sampling Noise for Efficient RL of Flow-Matching Models Benjamin Yu, Ziyang Liu, Justin Cui WS76
AAAI26_W15_18 Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models Madison Van Doren, Casey Ford WS77
AAAI26_W15_19 SafeGen: Benchmarking Inference-Time Methods for Privacy-Preserving Text Generation Aravilli Atchuta Ram WS78
AAAI26_W15_20 BLUFF-1000: Measuring Uncertainty Expression in RAG Ron Zharzhavsky, Emma Wong, Daniel Ketema WS79
AAAI26_W15_22 Reasoning Models are Test Exploiters: Rethinking Multiple Choice Narun Krishnamurthi Raman, Taylor Lundy, Kevin Leyton-Brown WS80
AAAI26_W15_24 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 WS81
AAAI26_W15_27 LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval Elliot L Epstein, John Winnicki, Thanawat Sornwanee, Rajat Vadiraj Dwaraknath WS82
AAAI26_W15_28 Know Or Not: a library for systematically evaluating out-of-knowledge-base robustness Jessica Foo, Pradyumna Shyama Prasad, Shaun Khoo WS83
AAAI26_W15_29 Next-Frame Prediction as a Reliability-Aware Training Paradigm for Robust Vision Encoders Marcel Simon, Eunbin Lee, Tae-Ho Kim, Seul-Ki Yeom WS84
AAAI26_W15_34 Beyond Blind Spots: Analytic Hints for Mitigating LLM-Based Evaluation Pitfalls Ora Nova Fandina, Gal Amram, Eitan Farch, Shmulik Froimovich, Raviv Gal, Wesam Ibraheem, Rami Katan, Alice Podolsky, Orna Raz WS85
AAAI26_W15_36 Future Is Unevenly Distributed: Forecasting Ability Of LLMs Depends On What We’re Asking Chinmay Karkar, Paras Chopra WS86
AAAI26_W15_38 Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles Wang Ma, Debarun Bhattacharya, Junkyu Lee, Nhan H Pham, Harsha Kokel, Qiang Ji WS87
AAAI26_W15_39 Prompt-Adaptive Quantization: Adaptive Per-Prompt Routing for Efficient LLM Inference Gabriel Jimenez, Vivann Khanna, Rishi Sastri, Raine Ma, Soham Chatterjee, Kevin Zhu, Sunischal Dev WS88
AAAI26_W15_52 BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision Language Models Sunny Gupta, Shounak Das, Amit Sethi WS89
AAAI26_W15_54 COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation Kenji Sahay, Snigdha Pandya, Rohan Nagale, Anna Lin, Shikhar Shiromani, Kevin Zhu, Sunischal Dev WS90

Oral Sessions Schedule:

Presentation 1: Task Interference in VLMs for Autonomous Driving: When Better Perception Hurts Planning
Presenter: Aadya Pipersenia, Honda Japan

Presentation 2: Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning
Presenter: Svetlana Churina, National University of Singapore

Presentation 3: LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
Presenter: Elliot Epstein, Stanford University

Presentation 4: Next-Frame Prediction as a Reliability-Aware Training Paradigm for Robust Vision Encoders
Presenter: Marcel Simon, Nota AI

Presentation 5: Future Is Unevenly Distributed: Forecasting Ability Of LLMs Depends On What We’re Asking
Presenter: Chinmay Karkar, Lossfunk India

Poster Location and Setup

All posters for Bridges and Workshops will be located on Level 2 of the Singapore EXPO (not in the Expo Halls).
The poster boards are double-sided and arranged in an accordion formation. Each poster board will have a number displayed on it (e.g., WS68, WS69, WS70, …).
Material required to put up the poster will be provided by AAAI.

Presenter Guidelines:

  • Use size A0 posters in portrait orientation - fastening materials will be provided
  • Display their posters on the day of their poster session - not the evening before.
  • Remove their posters at the end of the poster session to prevent loss
  • AAAI is not responsible for posters that are misplaced or stolen

location