AFM @ NeurIPS 2024

112 papers

Top Research Directions

Research directions most represented by AFM @ NeurIPS 2024 papers.

Reducing the Memory and Latency of Language Model Inference 3
Pluralistic Alignment for Heterogeneous Human Preferences 2
Overcoming the Limits of Multi Step Language Model Reasoning 2
Direct Preference Optimization 2
Dynamic Evaluation for Rapidly Evolving Language Models 2
The Decoupling of Visual Perception and Logical Reasoning 2
Grounding Language Models with External Knowledge Retrieval 2
Generalizing Deep Learning Methods Beyond Image Classification 2
Knowledge Retention in Continual Deep Learning 2
Non-Uniform Timestep Scheduling for Diffusion Models 1
Mitigating Bilinear Inconsistency in Federated Low-Rank Adaptation 1
Safety Alignment Degradation in Long Contexts 1
Autonomous Help Seeking for Uncertain Agents 1
Reinforcement Learning Within the Transformer Context Window 1
Implicit Gradient Descent in Transformer Forward Passes 1

Top Authors

AuthorPapers
Aishwarya Agrawal4
Huaxiu Yao4
Yujin Tang4
Beidi Chen3
Quanquan Gu3
Russ Salakhutdinov3
Yangfan He3
Zhuoming Chen3
Adriana Romero-Soriano2
Alexander Nikulin2
Christoph Dann2
David E. Keyes2
Di Wang2
Dongyoon Han2
Edoardo Cetin2
Eric P. Xing2
Frank Hutter2
Gang Li2
Hao Cheng2
Huizhuo Yuan2

Impactful Papers

Papers from AFM @ NeurIPS 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
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
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

« prev Page 3/3