Alexandre Rame
13 papers · 2021–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (25) π Keyword Champion (3)
π₯
Mega-Team Β· Squad
ποΈ
Keyword Collector
(61)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(12)
Application Areas
(7)
Learning Types Β· Machine Learning
(6)
Artificial Intelligence
(5)
Deep Learning
(4)
Core AI
(4)
Optimization & Theory
(4)
Natural Language Processing
(3)
Architectures
(3)
Resources & Methods
(3)
Reinforcement Learning
(2)
Core Methods
(2)
Learning Paradigms
(2)
Methods
(2)
Learning Types Β· Deep Learning
(1)
Keywords
out-of-distribution generalization
(3)
weight averaging
(3)
knowledge distillation
(2)
reinforcement learning from human feedback
(2)
domain generalization
(2)
model merging
(2)
ensemble learning
(2)
distribution shift
(2)
large language model
(2)
transfer learning
(1)
in-context learning
(1)
data augmentation
(1)
multimodal learning
(1)
instruction following
(1)
continual learning
(1)
model calibration
(1)
adversarial learning
(1)
model recycling
(1)
model alignment
(1)
information bottleneck
(1)
Papers
BOND: Aligning LLMs with Best-of-N Distillation
ICLR 2025
Diversity-Rewarded CFG Distillation
ICLR 2025
On Teacher Hacking in Language Model Distillation
ICML 2025
Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
ICLR 2024
Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning
EMNLP 2024
WARM: On the Benefits of Weight Averaged Reward Models
ICML 2024
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization
ICML 2023
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
NeurIPS 2023
Diverse Weight Averaging for Out-of-Distribution Generalization
NeurIPS 2022
DyTox: Transformers for Continual Learning With DYnamic TOken eXpansion
CVPR 2022
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
ICML 2022
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
ICLR 2021
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
ICCV 2021