Nicolas Flammarion
~Nicolas_Flammarion1
14
论文总数
7.0
年均投稿
平均评分
接收情况12/14
会议分布
ICLR
8
ICML
3
NeurIPS
3
发表论文 (14 篇)
20259 篇
4
Does Refusal Training in LLMs Generalize to the Past Tense?
ICLR 2025Poster
4
Simplicity Bias and Optimization Threshold in Two-Layer Networks
ICLR 2025Rejected
4
Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks
ICML 2025Poster
4
Long-Context Linear System Identification
ICLR 2025Poster
7
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
ICLR 2025Poster
3
Learning In-context $n$-grams with Transformers: Sub-$n$-grams Are Near-Stationary Points
ICML 2025Poster
3
Learning Parametric Distributions from Samples and Preferences
ICML 2025Spotlight
5
Selective Induction Heads: How Transformers Select Causal Structures in Context
ICLR 2025Poster
3
Is In-Context Learning Sufficient for Instruction Following in LLMs?
ICLR 2025Poster
20245 篇
4
Implicit Bias of Mirror Flow on Separable Data
NeurIPS 2024Poster
4
SGD vs GD: Rank Deficiency in Linear Networks
NeurIPS 2024Poster
4
First-order ANIL provably learns representations despite overparametrisation
ICLR 2024Poster
5
Why Do We Need Weight Decay in Modern Deep Learning?
ICLR 2024withdrawn
5
Why Do We Need Weight Decay in Modern Deep Learning?
NeurIPS 2024Poster