| 3271. |
Apple Conformer-Based Speech Recognition on Extreme Edge-Computing Devices (arxiv.org) |
|
3 points by walterbell on Apr 27, 2025 | hide | past | pdf | discuss
|
|
| 3272. |
Do Large Language Models know who did what to whom? (arxiv.org) |
|
39 points by badmonster on Apr 27, 2025 | hide | past | pdf | 5 comments
|
|
| 3273. |
LiDPM: Rethinking Point Diffusion for Lidar Scene Completion (arxiv.org) |
|
2 points by badmonster on Apr 27, 2025 | hide | past | pdf | discuss
|
|
| 3274. |
Sleep-Time Compute: Beyond Inference Scaling at Test-Time (arxiv.org) |
|
2 points by Jerry2 on Apr 26, 2025 | hide | past | pdf | discuss
|
|
| 3275. |
Empowering AI to Generate Better AI Code: Generation of DL Projects with LLMs (arxiv.org) |
|
1 point by belter on Apr 26, 2025 | hide | past | pdf | discuss
|
|
| 3276. |
Learning a Driving Simulator (2016) (arxiv.org) |
|
1 point by lambdaone on Apr 26, 2025 | hide | past | pdf | 1 comment
|
|
| 3277. |
Do Large Language Models Understand Logic or Just Mimick Context? (2024) (arxiv.org) |
|
2 points by indigodaddy on Apr 25, 2025 | hide | past | pdf | discuss
|
|
| 3278. |
Lossless LLM compression for efficient GPU inference via dynamic-length float (arxiv.org) |
|
411 points by CharlesW on Apr 25, 2025 | hide | past | pdf | 117 comments
|
|
| 3279. |
Paper2Code: Automating Code Generation from Scientific Papers (arxiv.org) |
|
133 points by Jerry2 on Apr 25, 2025 | hide | past | pdf | 27 comments
|
|
| 3280. |
LLMs with the Model Context Protocol Allow Major Security Exploits (arxiv.org) |
|
2 points by abhisek on Apr 25, 2025 | hide | past | pdf | discuss
|
|
| 3281. |
Extended Memory Architecture for Long-Context AI Conversations (arxiv.org) |
|
2 points by haebom on Apr 25, 2025 | hide | past | pdf | discuss
|
|
| 3282. |
Sleep-Time Compute: Beyond Inference Scaling at Test-Time (arxiv.org) |
|
1 point by anishathalye on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3283. |
PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch (arxiv.org) |
|
84 points by mfiguiere on Apr 24, 2025 | hide | past | pdf | 8 comments
|
|
| 3284. |
Three things everyone should know about Vision Transformers (arxiv.org) |
|
71 points by reqo on Apr 24, 2025 | hide | past | pdf | 17 comments
|
|
| 3285. |
Rethinking the Effectiveness of the LLM for Time Series Forecasting (arxiv.org) |
|
1 point by PaulHoule on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3286. |
Improving RAG for Personalization with Author Features and Contrastive Examples (arxiv.org) |
|
1 point by PaulHoule on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3287. |
Large-Scale Scene View Synthesis via Adaptive Block-Based Gaussian Splatting (arxiv.org) |
|
2 points by PaulHoule on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3288. |
Does RL Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (arxiv.org) |
|
2 points by Anon84 on Apr 24, 2025 | hide | past | pdf | 2 comments
|
|
| 3289. |
A Comprehensive Benchmark for C-to-Safe-Rust Transpilation (arxiv.org) |
|
2 points by azhenley on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3290. |
Ctrl-Z: Controlling AI Agents via Resampling (arxiv.org) |
|
1 point by JumpCrisscross on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3291. |
AtlasD: Automatic Local Symmetry Discovery[pdf] (arxiv.org) |
|
2 points by kelseyfrog on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3292. |
Improving Learning to Optimize Using Parameter Symmetries[pdf] (arxiv.org) |
|
2 points by kelseyfrog on Apr 24, 2025 | hide | past | pdf | discuss
|
|
| 3293. |
Double Descent Demystified: size of smallest non-zero singular value of X (arxiv.org) |
|
8 points by highfrequency on Apr 23, 2025 | hide | past | pdf | 1 comment
|
|
| 3294. |
Everybody Prune Now: Structured Pruning of LLMs with Only Forward Passes (arxiv.org) |
|
2 points by PaulHoule on Apr 23, 2025 | hide | past | pdf | discuss
|
|
| 3295. |
UI-Tars: Pioneering Automated GUI Interaction with Native Agents (arxiv.org) |
|
1 point by johnsutor on Apr 23, 2025 | hide | past | pdf | discuss
|
|
| 3296. |
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis (arxiv.org) |
|
1 point by PaulHoule on Apr 23, 2025 | hide | past | pdf | discuss
|
|
| 3297. |
Hands-On: Segmenting Individual Signs from Continuous Sequences (arxiv.org) |
|
1 point by PaulHoule on Apr 23, 2025 | hide | past | pdf | discuss
|
|
| 3298. |
Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad (arxiv.org) |
|
1 point by newswasboring on Apr 23, 2025 | hide | past | pdf | discuss
|
|
| 3299. |
Detecting Malicious Source Code in PyPI Packages with LLMs (arxiv.org) |
|
2 points by abhisek on Apr 23, 2025 | hide | past | pdf | 1 comment
|
|
| 3300. |
ChatTS: Aligning Time Series with LLMs via Synthetic Data (arxiv.org) |
|
3 points by duck on Apr 22, 2025 | hide | past | pdf | discuss
|
|
|
| More |
