Hacker Papers
- 601
ConvNets Match Vision Transformers at Scale
Hacker News threads
- Oct 2023ConvNets Match Vision Transformers at Scale
- Oct 2023ConvNets Match Vision Transformers at Scale
- Oct 2023ConvNets Match Vision Transformers at Scale
- Mar 2024The Google employees who created transformers
- Apr 2024Vision Transformers Are Overrated
- Apr 2024Vision Transformers Are Overrated
- Sep 2025Automatic differentiation can be incorrect
- Dec 2025The Illustrated Transformer
- 602
Optimizing Datalog for the GPU
Hacker News threads
- 603
Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Hacker News threads
- Apr 2026Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs
- Apr 2026Alignment Whack-a-Mole
- Apr 2026Finetuning Activates Verbatim Recall of Copyrighted Books in LLMs
- Mar 2026The Claude Code Source Leak: fake tools, frustration regexes, undercover mode
- Apr 2026AI Code Is Hollowing Out Open Source, and Maintainers Are Looking the Other Way
- Jun 2026US holds off blacklisting China's DeepSeek, +100 firms deemed security risks
- Jul 2026Claude Code Is Steganographically Marking Requests
- 604
Building up spacetime with quantum entanglement
Hacker News threads
- 605
The Alcubierre Warp Drive: On the Matter of Matter
Hacker News threads
- 606
Practical recommendations for gradient-based training of deep architectures
Hacker News threads
- 607
Matter-wave interference with particles selected from a molecular library with masses exceeding 10000 amu
Hacker News threads
- 608
Many Worlds, the Born Rule, and Self-Locating Uncertainty
Hacker News threads
- 609
Semi-Supervised Learning with Ladder Networks
Hacker News threads
- 610
Learning to Generate Reviews and Discovering Sentiment
Hacker News threads
- 611
The Curious Case of Neural Text Degeneration
Hacker News threads
- 612
Insecure Until Proven Updated: Analyzing AMD SEV's Remote Attestation
Hacker News threads
- 613
Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
Hacker News threads
- 614
Locally Typical Sampling
Hacker News threads
- 615
An Overview on IEEE 802.11bf: WLAN Sensing
Hacker News threads
- 616
Shor's Algorithm Does Not Factor Large Integers in the Presence of Noise
Hacker News threads
- 617
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
Hacker News threads
- 618
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Hacker News threads
- 619
Large Concept Models: Language Modeling in a Sentence Representation Space
Hacker News threads
- 620
Qwen3 Technical Report
Hacker News threads
- Feb 2026Consistency diffusion language models: Up to 14x faster, no quality loss
- May 2026An OpenAI model has disproved a central conjecture in discrete geometry
- Jul 2026What happens behind the scenes when we change effort for same LLM models?
- Aug 2026Meta Muse Glimmer – open weights 30B local coding model
- 621
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Hacker News threads
- 622
Spontaneous Inflation and the Origin of the Arrow of Time
Hacker News threads
- 623
Experimental realization of Shor's quantum factoring algorithm using nuclear magnetic resonance
Hacker News threads
- 624
Circuit for Shor's algorithm using 2n+3 qubits
Hacker News threads
- 625
Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Hacker News threads
- Jan 2018Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks
- Mar 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Apr 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Jan 2019This clever AI hid data from its creators to cheat at its appointed task
- May 2019TensorFlow Graphics: Computer Graphics Meets Deep Learning
Data from the Hacker News archive (ODC-By), arXiv and OpenAlex. Not affiliated with Hacker News or Y Combinator.