ICML 2024 Past Large language models
ICML 2024 Workshop on Foundation Models in the Wild
ICML 2024 FM-Wild Workshop
- Submission deadline
- Jun 8, 2024, 12:29 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (95)
Fetched from OpenReview (v2) on 2026-06-10.
-
$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
-
A Critical Look At Tokenwise Reward-Guided Text Generation
-
Adapting LLM Agents with Universal Feedback in Communication
-
Adaptive Concept Bottleneck for Foundation Models
-
AdaptiveBackdoor: Backdoored Language Model Agents that Detect Human Overseers
-
Adversarially Robust CLIP Models Induce Better (Robust) Perceptual Metrics
-
An Auditing Test to Detect Behavioral Shift in Language Models
-
An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Foundation Models
-
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
-
Bilingual Adaptation of Monolingual Foundation Models
-
Black-Box Detection of Language Model Watermarks
-
BUILD: Buffer-free Incremental Learning with OOD Detection for the Wild
-
Calibrated Self-Rewarding Vision Language Models
-
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
-
CharED: Character-wise Ensemble Decoding for Large Language Models
-
Code Agents are State of The Art Software Testers
-
Combining Pre-trained LoRA Modules Improves Few-shot Adaptation of Foundation Models to New Tasks
-
ContextCite: Attributing Model Generation to Context
-
Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?
-
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
-
DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection
-
Domain-Aware Fine-Tuning of Foundation Models
-
Dual Risk Minimization for Robust Fine-tuning of Zero-Shot Models
-
Efficient Evolutionary Search over Chemical Space with Large Language Models
-
End-To-End Causal Effect Estimation from Unstructured Natural Language Data
-
Estimating Probability Densities of Tabular Data using a Transformer Model combined with Denoising Diffusion
-
Evaluating Self-Supervised Foundation Models in Holographic Imaging
-
Evaluation of RAG Metrics for Question Answering in the Telecom Domain
-
ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
-
Extracting Training Data from Document-Based VQA Models
-
Extrapolative Protein Design through Triplet-based Preference Learning
-
Federated Fine-Tuning of Vision Foundation Models via Probabilistic Masking
-
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
-
FoMu-SSL: Foundation Model-Guided Multi-Sensor Self-Supervised Learning for Remote Sensing
-
Generalization vs. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data
-
Geometric Median Matching for Robust Data Pruning
-
GROD: Enhancing Generalization of Transformer with Out-of-Distribution Detection
-
Improving GFlowNets for Text-to-Image Diffusion Alignment
-
Improving Graph-Language Alignment with Hierarchical Graph Tokenization
-
In Search of Forgotten Domain Generalization
-
In-Context Learning Improves Compositional Understanding of Vision-Language Models
-
Inference Performance Optimization for Large Language Models on CPUs
-
InstructBooth: Instruction-following Personalized Text-to-Image Generation
-
Instruction Tuning With Loss Over Instructions
-
Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data
-
It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF
-
Jogging the Memory of Unlearned Models Through Targeted Relearning Attacks
-
Language Model-In-The-Loop: Data Optimal Approach to Recommend Actions in Text Games
-
Leveraging Generative Foundation Models for Domain Generalization
-
LIFTED: Multimodal Mixture-of-Experts for Clinical Trial Outcome Prediction
-
LLM Task Interference: Impact of Task-Switch in Conversational History
-
LoRD: Low-Rank Decomposition of Monolingual Code LLMs for One-Shot Compression
-
Merging Improves Self-Critique Against Jailbreak Attacks
-
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge?
-
Model Breadcrumbs: Scalable Upcycling of Finetuned Foundation Models via Sparse Task Vectors Merging
-
MoRe Fine-Tuning with 10x Fewer Parameters
-
Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators
-
On the Discrepancy and Connection between Memorization and Generation in Diffusion Models
-
On the Privacy Risks of Post-Hoc Explanations of Foundation Models
-
Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives
-
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
-
Out-Of-Context Prompting Boosts Fairness and Robustness in Large Language Model Predictions
-
PanSAM: Zero-Shot, Prompt-Free Pancreas Segmentation in CT Imaging
-
Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis
-
PLUTO: Pathology-Universal Transformer
-
POST: A Framework for Privacy of Soft-prompt Transfer
-
Pretrained Hybrids with MAD Skills
-
Privacy Auditing of Large Language Models
-
Private Fine-tuning of Large Language Models with Zeroth-order Optimization
-
Projected Language Models: A Large Model Pre-Segmented Into Smaller Ones
-
Quantum 3D Visual Grounding: A Step Towards Quantum-inspired AI-Visualization
-
Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters
-
Recursive Introspection: Teaching LLM Agents How to Self-Improve
-
RNR: Teaching Large Language Models to Follow Roles and Rules
-
RouteFinder: Towards Foundation Models for Vehicle Routing Problems
-
SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound
-
Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
-
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
-
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
-
Strong Copyright Protection for Language Models via Adaptive Model Fusion
-
Test-Time Prototype Evolution for Generalizable Vision-Language Models
-
The Effect of Data Corruption on Multimodal Long Form Responses
-
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
-
Towards Safe Large Language Models for Medicine
-
TriLM vs FloatLM: Ternary LLMs are more Performant than Quantized FP16 LLMs
-
Two-Level Test-Time Adaptation in Multimodal Learning
-
Understanding the Role of Functional Diversity in Weight-Ensembling with Ingredient Selection and Multidimensional Scaling
-
Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices
-
Unveiling CLIP Dynamics: Linear Mode Connectivity and Generalization
-
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
-
VFA: Vision Frequency Analysis of Foundation Models and Human
-
Vision-Language Models Provide Promptable Representations for Reinforcement Learning
-
Waterfall: Framework for Robust and Scalable Text Watermarking
-
When Do Language Models Need to Be Large?
-
Zero-Shot Generalization of GNNs over Distinct Attribute Domains