Skip to yearly menu bar Skip to main content


Affinity Event Fri, Dec 11, 2026 • 11:00 PM – 4:00 AM AEDT Palais des congrès Room 152

NewInML

Ariankh
Chat is not available.

Schedule

Time zone: Conference local time zone
SIMPATIX: Transformer-Based Depression Prediction from Social Media Posts
Bhavya Thakur ⋅ Raghavendra Thakur ⋅ Madhavendra Thakur
System-Prompt Personalization for Open-Weight Models in Multi-Turn RAG
Erin MacNeil ⋅ Scott Bateman ⋅ Mahtab Sarvmaili
SPIRE: Learning Shared–Private Neural Structure for Perturbation Analysis
Rahil Soroushmojdehi ⋅ Sina Javadzadeh ⋅ Mehrnaz Asadi ⋅ Terence Sanger
Profile-Based Auditing of Domestic Violence Survey Selection Across South Asia
Mohammad Abu Obaida Mullick ⋅ Rezaur Rahman Ratul ⋅ Mymuna Nourin ⋅ Motaharul Islam
NetFlow-JEPA: Temporal Self Supervised Graph Based Network Intrusion Detection
Naman Batra ⋅ Raj Raman ⋅ Chirag Miglani ⋅ Vimanyu singh ⋅ AARTI JAIN
Should Register Foundation Models Be Part of Pandemic Preparedness?
Thomas A Eriksson ⋅ Adam Altmejd ⋅ Anders Björkelund ⋅ Dominik Dietler ⋅ Maxim Kan ⋅ Anna M Ekström ⋅ Fredrik Kahn ⋅ Mattias Ohlsson ⋅ Jonas Björk
Conformal Prediction Under Physical Constraints for Scientific Surrogates
Vijay Chopra ⋅ Prajesh Mishra ⋅ Ajay Aravanan ⋅ Vasilisa Baginskaya ⋅ Kiran Nijjer
Cheap Online Monitoring Helps: Case Study on nanochat
Maksym Khavil ⋅ Ryan Y Xu ⋅ Martin Schmid
Separating Injection Presence from Executor Compromise in Residual-Stream Probes of Multi-Agent LLM Pipelines
Mariame Diabate ⋅ Ifeoluwa Jayeola ⋅ Oudoum Ali Houmed ⋅ Eyiara Oladipo ⋅ Elena Ajayi ⋅ Anagha Late ⋅ Lawrence T Wagner
Three Domains, One Direction: Reasoning-Calibration Steering Transfers Across Domains
Yung-Hsuan Yang ⋅ Wenyu Wang ⋅ Justin Tandon ⋅ Akhilesh Bitla ⋅ Madhur Panwar ⋅ Kevin Zhu ⋅ Anusha Mujumdar
When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM Answering
Saanvi Paturi ⋅ Arsen Kenzhebayev ⋅ Arham Sethi ⋅ Vyas Raina ⋅ Ivaxi Sheth ⋅ Vatsal Raina
Ontoscope: Ontology-Guided Retrieval Scoping for Efficient Retrieval-Augmented Generation
Dhananjay Khulbe ⋅ Siddarth Tumu ⋅ Siddharth Mahesh ⋅ Jonathan Wang
From Scaling Tests to Production: Dense LLM Pretraining on Leonardo
Emilia Cozzolino ⋅ Domitilla Brandoni ⋅ Filippo Festa ⋅ Davide Gentile ⋅ Riccardo Scheda ⋅ Michele Visciarelli
Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return
Arham Sethi ⋅ Arsen Kenzhebayev ⋅ Saanvi Paturi ⋅ Vatsal Raina ⋅ Vyas Raina ⋅ Ivaxi Sheth
CareQueue: Reinforcement Learning Methods for Intelligent Patient Prioritization
Ayush Jain ⋅ Julia Kryłowicz ⋅ Beloslava Malakova ⋅ Anusha Asthana
CONE: A Benchmark for Verifying Counting Reliability in Open-Weight LLMs
Ishaan Verma ⋅ Arsheya Yadav ⋅ Tanvi Bajpai ⋅ Shubh Maheshwari ⋅ Lakshay Verma
Verbalizable Representations Emerge before Workspace Functions in Language Models
Arjun Dabir ⋅ Ailun Shen ⋅ Michael Chan ⋅ Bangzishu Huang ⋅ Shanduojiao Jiang ⋅ Mohammed Mahfoud
Systematic Literature Review for Computational Detection of Anthropomorphic Language
Shumaim liaquat ⋅ Rabeea Jaffari ⋅ Areej F Meghji ⋅ Faiz Nadeem
When Verifiers Disagree: Measuring Specification Sensitivity in Jailbreak Evaluation
Saleena Angeline Sartawita ⋅ Amy Xie ⋅ Arjun Addaypally ⋅ Shobhnik Kriplani
Delta Attention Residuals for Cross-Layer Information Flow in Indic Models
Vaibhav Verma ⋅ Sanyam Jain ⋅ Chintakrindi K Kartik
Measuring impact of evaluation format on LLM-as-a-Judge for Long-Form Audio Reasoning
Abijah Sanjeev ⋅ AnaLuz Ferrer ⋅ Sarayu Badam ⋅ Aydin Feroz ⋅ Arjun Bahuguna
Symmetry Alignment Across Depth in Transformer Merging
Krish Malik ⋅ Tasmayu Swain ⋅ Krishna Mudgal
Adversarial Attacks Expose Path-Dependent Failures in Discrete Medical Image Tokenizers
Ahmed Loughzali ⋅ Akash Yallamati ⋅ Aadiv Reki ⋅ Aslan Vaida ⋅ Jeyashree Krishnan
Architectures and KV Replay for Depth-Recurrent Language Models
Lucia Licakova ⋅ Lukas Hauzenberger ⋅ Niklas Schmidinger ⋅ Sebastian Böck ⋅ Sepp Hochreiter
Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit
Shuyi Fan ⋅ Boyuan Deng ⋅ Mengyu Xu ⋅ Xinhong Xie ⋅ Chenyang Li ⋅ Hongyang Zhang
Measuring Provenance Sensitivity in Tool-Using LLM Agents Reveals Channel-Dependent Safety Behavior
Raghav R Jayanthi ⋅ Mahima Sachan ⋅ Bhagyesh Rathi ⋅ Mukul D Chhangani ⋅ Ajay M Rangarajan
Bounds for Universal Representation with Spiking Neural Networks
Aston Wan ⋅ Evan Zhao ⋅ Nathan Yan ⋅ Cooper Sigrist
POSTURE: A Multimodal Movie Clip Dataset for Contrastive Pose Embedding
Yuchen Wei ⋅ Aaron Ely ⋅ Henry Wei ⋅ Cooper Sigrist
Search Pathology Diagnosis for Automated Discovery
Alistair Liang Chuen Cheong ⋅ Zerui Chen ⋅ Soham Raychaudhuri ⋅ Seungone Kim ⋅ Young-Jun Lee ⋅ Dongyeop Kang
Semantic-Aware Logit Adjustment for Long-Tailed Recognition
Brainard P Jagati ⋅ Jitendra Tembhurne ⋅ Ananya K Patel ⋅ Animesh R Tripathi ⋅ Harsh Goud
Replay-Augmented Dynamic Data Pruning for Image Classification
Lisa Rumplmayr ⋅ Eva Gubler ⋅ Huiting Tang ⋅ Arsen Yermukan
From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search
Corrado Calamita ⋅ Matteo Mendicini ⋅ Riccardo Bertamini ⋅ Luca Ferrari
Reconstructing High-Resolution Hyperparameter Loss Landscapes via Active Surrogate Modeling
Shihao Ji ⋅ Junshan Mu ⋅ YiZhou Huang ⋅ Yeung Y Thomas
What Does Language Alter Medical Vision-Language Model Decisions Across Domains? A Seven-Language Chest X-Ray Study
Ayoub Louaye Bouaziz ⋅ Douaa M Yagoub ⋅ Iliam Souami ⋅ zein miled ⋅ Ilyes sais ⋅ Nadjiba Rahal ⋅ Basma Halil ⋅ Chemam soundous ⋅ REZZOUG AICHA ⋅ Lokmane Chebouba
XpertGPT: Efficient Language Modeling via Multi-Scale Sparse Expert Routing
Soham Jain ⋅ Harsh Singh ⋅ Divija Dewan ⋅ Atul Dev
Evaluating Context-Window Harnesses for CBRNE Safety
Nathan Nguyen ⋅ Nicholas Kim ⋅ Abhitha Vegi ⋅ Arko Samad ⋅ Suvajit Majumder
MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference
Michael Wang ⋅ Keith Li ⋅ Roozbeh Bostandoost
PeerConf: Self-Calibrating Early Stopping for Efficient Parallel LLM Reasoning
Mofe Atanda ⋅ Yani Baguenane ⋅ Tyler Yi ⋅ Deniz Filiz ⋅ Mohammed Mahfoud ⋅ Anusha Mujumdar
Q-JEPA: Joint-Embedding Predictive Adaptation for Quantized Large Language Models
Chaitanya Kakade ⋅ Dhiraj Salunkhe ⋅ Gaurang Kakade
Country Is Not Enough: Recognition - Action Gaps in Cultural Answerability
Aditya Channa ⋅ Madhav Kapoor ⋅ Jastej Singh
Multi-modal Latent Predictive Architectures for Heterogeneous Clinical Data
Daniyal Selani ⋅ Erik B van den Akker ⋅ Marcel Reinders
Not All Attention Is Created Equal: Robustness of In-Context Learning Across Attention Mechanisms
Ken Zheng ⋅ Joshua Lu ⋅ Lenci Ni ⋅ Tiger Zhang ⋅ William Li
Slot Attention and K-means
Vasudev Joy ⋅ Rajat Rasal ⋅ Anthea Monod ⋅ Ben Glocker ⋅ Avinash Kori
SegmentWeave: Post-Processing framework for Enhanced Dense Video Captioning
Seunghwan Seo ⋅ Junhyuk Kwon ⋅ Hongjoo Kim ⋅ Kang Daemin ⋅ Nayoung Park ⋅ Hanseong Lee ⋅ Kyle Min
Comparing General and Failure-Mode Targeted Synthetic Datasets for Bounding-Box Object Detection
Jonathan Wang ⋅ Siddharth Mahesh ⋅ Siddarth Tumu ⋅ Dhananjay Khulbe
Marginals by Flows, Dependence by Energy: Learning Multimodal Joint Distributions
Sebastien Grand ⋅ Aurelie Montarnal ⋅ Guillaume Pouget ⋅ Piffault Charles ⋅ Bruno Mériaux ⋅ Frederick Benaben
WAHM: Measuring Hallucination Drift Across Arabic Varieties
Mujtaba farhan ⋅ Muhammad Kamran J Khan
Subliminal Traits Persist Through Distillation.
Abass Oguntade ⋅ Shivam Arora
Predicting Protection Strength for Diffusion-Based Image Editing Without the Attacker's Model
Saarthak Gupta ⋅ Vasu Mahajan ⋅ Arjun K Tomar ⋅ Vedant K Shanker
MDM-OC: Orthogonal Delta Merging for Scalable and Reversible Model Composition
Haris Khan ⋅ Sadia Asif ⋅ Shumaila Asif ⋅ Muhammad Zeeshan Karamat ⋅ Rajesh Upadhayaya
Evaluating LALM Judges on Freeform Audio Reasoning
Jordan Zhang ⋅ Rohith Reddy Mandala ⋅ Hardev Ranglani ⋅ Arjun Bahuguna
"Close enough?'' An investigation into multiplication errors in LLMs
William Bolton ⋅ Bezawit Lake Tilaye ⋅ Huw Day