Search: openreview.net | Heykuki News

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Study identifies weaknesses in how AI systems are evaluated (oii.ox.ac.uk)

416 points

7 months ago

2.

Launch HN: Humanloop (YC S20) – A platform to annotate, train and deploy NLP

157 points

6 years ago

3.

Launch HN: Roundtable (YC S23) – Using AI to Simulate Surveys

121 points

3 years ago

4.

Show HN: Open-Sourcing Google's Lattice Models in PyTorch (github.com/ControlAI)

13 points

3 years ago

5.

Show HN: Roundtable – Estimating survey results in seconds (roundtable.ai)

7 points

3 years ago

6.

Ask HN: Feasible to build open-source GATO Foundation Model?

3 points

3 years ago

7.

Ask HN: Some tips for evaluating intelligent agents?

2 points

2 years ago

8.

Show HN: ElasticMM – 4.2× Faster Multimodal LLM Serving (NeurIPS 2025 Oral)

1 point

6 months ago

9.

Show HN: Best Rejected Papers (deneutoy.github.io)

1 point

10 months ago

10.

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

1 point

a year ago

11.

Ask HN: Is there a mountain pick view concept in Reinforcement Learning?

1 point

4 years ago

12.

Measuring Compositional Generalization in ML Architectures

1 point

6 years ago

13.

30% drop in O1-preview accuracy when Putnam problems are slightly variated (openreview.net)

560 points

a year ago

14.

Word2Vec received 'strong reject' four times at ICLR2013 (openreview.net)

369 points

2 years ago

15.

Deep Learning for Symbolic Mathematics (openreview.net)

222 points

7 years ago

16.

Turing Complete Transformers: Two Transformers Are More Powerful Than One (openreview.net)

190 points

2 years ago

17.

Vision Transformers Need Registers (openreview.net)

171 points

2 years ago

18.

Symbolic Regression is NP-hard (openreview.net)

109 points

4 years ago

19.

Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs (openreview.net)

92 points

6 years ago

20.

Neural Architecture Search with Reinforcement Learning (openreview.net)

88 points

9 years ago

21.

Approximating CNNs with Bag-of-Local-Features Models [pdf] (openreview.net)

80 points

7 years ago

22.

A computational model of the Moth Olfactory Network learns to read MNIST [pdf] (openreview.net)

71 points

8 years ago

23.

Text Embeddings Reveal (Almost) as Much as Text (openreview.net)

66 points

3 years ago

24.

Large Language Models Are Human-Level Prompt Engineers (openreview.net)

64 points

3 years ago

25.

ImageNet-trained CNNs are biased towards texture (2019) (openreview.net)

60 points

6 years ago

26.

Learning to Represent Edits (openreview.net)

39 points

7 years ago

27.

Learning the Arrow of Time [pdf] (openreview.net)

36 points

7 years ago

28.

Learning to Design RNA (openreview.net)

36 points

human_scientist

7 years ago

29.

Winner’s Curse? On pace, progress, and empirical rigor [pdf] (openreview.net)

28 points

8 years ago

30.

Flow Map Learning via Nongradient Vector Flow [pdf] (openreview.net)

26 points

a month ago