TiFA @ ICML

14 papers24 directions

Papers by Year

2024 14

Top Research Directions

Research directions most represented by papers from this venue.

The Sufficiency of Memoryless Strategies 1
Solving Complex Games via Zero-Sum Reductions 1
The Inverse Scaling of Reasoning Faithfulness 1
Task Order Sensitivity in Continual Learning 1
Activation Steering for Inference Time Model Control 1
Sparse Temporal Adversarial Perturbations 1
Sample Efficient Learning for Specialized Domains 1
Loss Landscape Flattening for Sequential Learning 1
Game Theoretic Formulations for Adversarial Robustness 1
Direct Preference Optimization 1
The Fragility of Imperceptible Image Protections 1
Scaling Multimodal Fusion Beyond Pairwise Interactions 1
Overcoming the Digital to Physical Domain Gap 1
Task Activation via In Context Demonstrations 1
Learning from Incomplete Multimodal Data Streams 1

Top Authors

AuthorPapers
Adina Williams2
Yang Bai2
Abdul W Basit1
Abhishek Sureddy1
Adam Daneshmend1
Adam Ibrahim1
Adriana Romero-Soriano1
Alessandro Abate1
Alexis Roger1
Alicia Yi Sun1
Andreas Demosthenous1
Aviral Kumar1
Boryeong Cho1
Brando Miranda1
Buck Shlegeris1
Charlie Griffin1
Chirag Agarwal1
Claire Tomlin1
Daniel Z Kaplan1
Dan Ley1

Impactful Papers

Papers from this venue that shaped research clusters.

Influential

Papers

TitleYear
Bias Begets Bias: The Impact of Biased Embeddings on Diffusion Models2024
Borrowing Treasures from Neighbors: In-Context Learning for Multimodal Learning with Missing Modalities and Data Scarcity2024
Chained Tuning Leads to Biased Forgetting2024
Decomposed evaluations of geographic disparities in text-to-image models2024
Games for AI-Control: Models of Safety Evaluations of AI Deployment Protocols2024
On the Difficulty of Faithful Chain-of-Thought Reasoning in Large Language Models2024
On the Multi-modal Vulnerability of Diffusion Models2024
Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models2024
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques2024
TrustAgent: Towards Safe and Trustworthy LLM-based Agents through Agent Constitution2024
Unfamiliar Finetuning Examples Control How Language Models Hallucinate2024
VACoDe: Visual Augmented Contrastive Decoding2024
Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs2024
Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?2024