conftrace_

training loss

12 papers

Explore in graph

Co-occurring keywords

spike pattern (1) rawlsian fairness (4) variance minimization (10) demographic prior (1) experience replay (99) fairness optimization (28) demographic parity (75) mode collapse (102) classification task (45) transformer language model (192)

Papers

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning ACL 2026
Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets AAAI 2026
Design and Analysis of few Million Parameter Transformer-based Language Models trained over a few Million Tokens Dataset EMNLP 2025
No Simple Answer to Data Complexity: An Examination of Instance-Level Complexity Metrics for Classification Tasks NAACL 2025
Rethinking the Membrane Dynamics and Optimization Objectives of Spiking Neural Networks NIPS 2024
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior NIPS 2024
Prioritizing Samples in Reinforcement Learning with Reducible Loss NIPS 2023
Scaling of Class-wise Training Losses for Post-hoc Calibration ICML 2023
Provable Benefit of Mixup for Finding Optimal Decision Boundaries ICML 2023
Analyzing Gender Translation Errors to Identify Information Flows between the Encoder and Decoder of a NMT System EMNLP 2022
Embracing Ambiguity: Shifting the Training Target of NLI Models IJCNLP 2021
Do We Need Zero Training Loss After Achieving Zero Training Error? ICML 2020