PaperHub

Aaron Courville

~Aaron_Courville3

30
论文总数
15.0
年均投稿
6.2
平均评分
接收情况23/30
会议分布
ICLR
15
NeurIPS
6
ICML
5
COLM
4

发表论文 (30 篇)

202522

6.8
5

Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models

NeurIPS 2025Poster
7.4
5

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL

ICLR 2025Spotlight
4.3
4

Bias Analysis in Unconditional Image Generative Models

ICLR 2025Rejected
6.5
4

Neuroplastic Expansion in Deep Reinforcement Learning

ICLR 2025Poster
6.3
3

The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks

ICML 2025Poster
6.5
4

Scaling Stick-Breaking Attention: An Efficient Implementation and In-depth Study

ICLR 2025Poster
6.0
4

Sample, Predict, then Proceed: Self-Verification Sampling for Tool Use of LLMs

NeurIPS 2025Rejected
6.3
3

Adaptive Computation Pruning for the Forgetting Transformer

COLM 2025Poster
6.6
4

The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning

ICML 2025Poster
6.6
4

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

ICML 2025Poster
6.8
4

BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation

COLM 2025Poster
4.0
4

Training Universal Text Encoders with Pair Relevance Classification Loss

ICLR 2025Rejected
5.5
4

Not All LLM Reasoners Are Created Equal

ICLR 2025Rejected
6.8
4

Forgetting Transformer: Softmax Attention with a Forget Gate

ICLR 2025Poster
6.8
4

Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning

NeurIPS 2025Poster
5.5
4

FLAM: Frame-Wise Language-Audio Modeling

ICML 2025Poster
6.6
4

VinePPO: Refining Credit Assignment in RL Training of LLMs

ICML 2025Poster
5.8
4

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

ICLR 2025Poster
5.0
4

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

ICLR 2025Rejected
8.7
4

Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning

NeurIPS 2025Spotlight
7.5
4

Advantage Alignment Algorithms

ICLR 2025Oral
7.3
4

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

NeurIPS 2025Poster