NeurIPS 2024 Past Large language modelsEfficiency
Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning
AFM 2024
- Submission deadline
- Oct 5, 2024, 12:00 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 (128)
Fetched from OpenReview (v2) on 2026-06-10.
-
$\text{Transformer}^2$: Self-adaptive LLMs
-
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
-
Accelerated Preference Optimization for Large Language Model Alignment
-
AdaptAgent: Adapting Multimodal Web Agents with Few-Shot Learning from Human Demonstrations
-
Adapting Foundation Models via Training-free Dynamic Weight Interpolation
-
Adapting Language Models via Token Translation
-
Adaptive LoRA Merging for Efficient Domain Incremental Learning
-
Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity
-
Agent Skill Acquisition for LLMs via CycleQD
-
AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents
-
AoP-SAM: Automation of Prompts for Efficient Segmentation
-
APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
-
Approximate Top-k for Increased Parallelism
-
Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
-
Assisted Few-Shot Learning for Vision-Language Models in Agricultural Stress Phenotype Identification
-
Automated Design of Agentic Systems
-
Automatically Generating Custom Context-Driven SFT Data for LLMs with Multi-Granularity
-
Better Prompt Compression Without Multi-Layer Perceptrons
-
Can the Spectrum of the Neural Tangent Kernel Anticipate Fine-Tuning Performance?
-
Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?
-
CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models
-
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
-
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
-
Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
-
Controlling Forgetting with Test-Time Data in Continual Learning
-
Controlling Multimodal LLMs via Reward-guided Decoding
-
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement
-
CTRL-O: Language-Controllable Object-Centric Visual Representation Learning
-
Data-Efficient Training by Evolved Sampling
-
Deliberate Practice with Synthetic Data
-
Device-Directed Speech Detection for Follow-up Conversations Using Large Language Models
-
Do Think Tags Really Help LLMs Plan? A Critical Evaluation of ReAct-Style Prompting
-
Domain Adaptation for Robust Model Routing
-
DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach
-
Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models
-
Dynamically Managing a Prompt Pool via Self-Enhancement in Continual Learning
-
Effective Text-to-Image Alignment with Quality Aware Pair Ranking
-
Efficient Domain Adaptation of Robotic Foundation Models via Hypernetwork-Generated LoRA
-
Efficient Fine-Tuning of Image-Conditional Diffusion Models for Depth and Surface Normal Estimation
-
Efficient Transfer Learning driven by Layer-wise Features Aggregation
-
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
-
Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
-
Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning
-
Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation
-
Enhancing Fine-Tuning Efficiency of LLMs Through Gradient Subspace Tracking
-
Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
-
Enhancing Multi-Agent Multi-Modal Collaboration with Fine-Grained Reward Modeling
-
Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications
-
Ensemble-based Offline Reinforcement Learning with Adaptive Behavior Cloning
-
Evaluating RAG System Performance: The Impact of Knowledge Cut-off and Fine-Tuning
-
Exploring Visual Prompt Tuning for Demographic Adaptation in Foundation Models for Medical Imaging
-
Extracting Parallelism from Large Language Model Queries
-
Fast and Accurate Language Model Decoding via Parallel Token Processing
-
Fine-Grained Visual Recognition in the Age of Multimodal LLMs
-
Fine-tuning LLM Agents with Retrospective In-Context Online Learning
-
FlashDP: Memory-Efficient and High-Throughput DP-SGD Training for Large Language Models
-
From One to Zero: RAG-IM Adapts Language Models for Interpretable Zero-Shot Clinical Predictions
-
Fully-inductive Node Classification on Arbitrary Graphs
-
Generating Diverse Negations from Affirmative Sentences
-
Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
-
GraphText: Graph Reasoning in Text Space
-
IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning
-
Imbalance-Regularized LoRA: A Plug-and-Play Method for Improving Fine-Tuning of Foundation Models
-
Improving In-Context Learning with Small Language Model Ensembles
-
Improving Model Merging with Natural Niches
-
In-Context Learning behaves as a greedy layer-wise gradient descent algorithm
-
Informed Tree of Thought: Cost-efficient Problem Solving with Large Language Models
-
Instant Transformer Adaption via HyperLoRA
-
InstructRAG: Instructing Retrieval Augmented Generation via Self-Synthesized Rationales
-
InvestAlign: Align LLMs with Investor Decision-Making under Herd Behavior
-
Is In-Context Learning Sufficient for Instruction Following in LLMs?
-
LangDA: Language-guided Domain Adaptive Semantic Segmentation
-
Leveraging Self Weak-supervision for Improved VLM Performance
-
LinkGPT: Teaching Large Language Models To Predict Missing Links
-
Long Context RAG Performance of Large Language Models
-
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
-
MagicPIG: LSH Sampling for Efficient LLM Generation
-
MD-DiT: Step-aware Mixture-of-Depths for Efficient Diffusion Transformers
-
Memory Efficient Continual Learning with CLIP Models
-
MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees
-
metaTextGrad: Learning to learn with language models as optimizers
-
Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention
-
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
-
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
-
Model Developmental Safety: A Safety-Centric Method and Applications in Vision-Language Models
-
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
-
Narrow Transformer: Mono-lingual Code SLM for Desktop
-
NegMerge: Consensual Weight Negation for Strong Machine Unlearning
-
Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts
-
OmniPredict: GPT-4o Enhanced Multi-modal Pedestrian Crossing Intention Prediction
-
On Pre-training of Multimodal Language Models Customized for Chart Understanding
-
One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation
-
P3O: Pessimistic Preference-based Policy Optimization for Robust Alignment from Preferences
-
PAL: Pluralistic Alignment Framework for Learning from Heterogeneous Preferences
-
Personalized Adaptation via In-Context Preference Learning
-
Personalized Language Modeling from Personalized Human Feedback
-
Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
-
Personas within Parameters: Fine-Tuning Small Language Models with Low-Rank Adapters to Mimic User Behaviors
-
Pick Your Influencer: Being Selective is Good for Personalization
-
PM-Jewelry: Personalized Multimodal Adaptation for Virtual Jewelry Try-On with Latent Diffusion
-
Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer
-
Prompt Learning Based Adaptor for Enhanced Video Editing with Pretrained Text-to-Image Diffusion Models
-
RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems
-
REGENT: A Retrieval-Augmented Generalist Agent That Can Act in-Context In New Environments
-
Retrieval-Augmented Data Augmentation for Low-Resource Domain Tasks
-
SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
-
Self-Play Preference Optimization for Language Model Alignment
-
Sirius: Contextual Sparsity with Correction for Efficient LLM
-
Situated Instruction Following Under Ambiguous Human Intent
-
Slaying the HyDRA: Parameter-Efficient Hyper Networks with Low-Displacement Rank Adaptation
-
SpikingVTG: Saliency Feedback Gating Enabled Spiking Video Temporal Grounding
-
Synergistic Weak-Strong Collaboration by Aligning Preferences
-
Tensor Attention Training: Provably Efficient Learning of Higher-order Transformers
-
Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?
-
Towards Conversational AI for Spina Bifida Care
-
Towards Federated Low-Rank Adaptation with Rank Heterogeneity
-
Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning
-
Towards Personalized Language Models via Inference-time Human Preference Optimization
-
Towards Robust and Cost-Efficient Knowledge Unlearning for Large Language Models
-
Transfer Learning for Finetuning Large Language Models
-
Uncertainty-Penalized Direct Preference Optimization
-
Understanding Visual Concepts Across Models
-
Uniform Text-Motion Generation and Editing via Diffusion Model
-
ViPCap: Retrieval Text-based Visual Prompts for Lightweight Image Captioning
-
Visual Language Alignment Tuning
-
Warmstarting for Scaling Language Models
-
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
-
ZO-Offloading: Fine-Tuning LLMs with 100 Billion Parameters on a Single GPU