AI Paper Atlas

Research map / Benchmarks / AGNews

AGNews leaderboard

43 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on AGNews. Best accuracy: 98.19 (cwFedAvg, ICCV 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

AGNews · accuracy

43 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
198.19cwFedAvg
FastText
Class-Wise Federated Averaging for Efficient Personalization
ICCV 2025 · Appendix Table
Personalized and heterogeneous FL
297.39TinyProto-FTCommunication-Efficient Heterogeneous Federated Learning with Sparse Prototypes in Resource-Constrained Environments
AAAI 2026 · Table 3
Communication-efficient FL
395.1MixConfig
BERT
Mixing Configurations for Downstream Prediction
ICML 2026 · Table 1
Recognition and long-tail
494.53CB-LLMs w/ ACC
RoBERTa-base
Concept Bottleneck Large Language Models
ICLR 2025 · Table: Test accuracy of CB-LLM
Language, safety and interpretability
594.5Distilled student (teacher -> student): RoBERTa-Base -> RoBERTa-Medium
RoBERTa-Medium
On student-teacher deviations in distillation: does it pay to disobey?
NeurIPS 2023 · Table 3 (appendix)
Knowledge distillation
694.25ACTACT: an Attentive Convolutional Transformer for Efficient Text Classification
AAAI 2021 · Table 2
CNN design
794.2BP-Checkpointing
Llama 3.1 8B (QLoRA r=1)
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
ICML 2026 · Table 3
RNNs and normalization
893.94Finetune with Contrastive Regularization
SimCSE BERT
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
ICLR 2023 · Foundation-model results table
Self-supervised and contrastive
993.93SPE (Spikingformer w/ SPE)Positional Encoding for Spiking Transformers
ICML 2026 · text
Spiking networks
1093.8SINN (240D)Generalize Sentence Representation with Self-Inference
AAAI 2020 · Table 3
Language, safety and interpretability
33 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.