| 3211. |
Don't be lazy: CompleteP enables compute-efficient deep transformers (arxiv.org) |
|
4 points by nsdey on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3212. |
Cost-of-Pass: An Economic Framework for Evaluating Language Models (arxiv.org) |
|
1 point by JumpCrisscross on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3213. |
Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection (arxiv.org) |
|
3 points by PaulHoule on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3214. |
HalluMix Benchmark: Detecting Hallucinations in Real-World Scenarios (arxiv.org) |
|
2 points by rancar2 on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3215. |
(How) Do reasoning models reason? (arxiv.org) |
|
3 points by YeGoblynQueenne on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3216. |
Evaluating Frontier Models for Stealth and Situational Awareness (arxiv.org) |
|
2 points by badmonster on May 6, 2025 | hide | past | pdf | discuss
|
|
| 3217. |
Analyzing Modern Nvidia GPU Cores (arxiv.org) |
|
178 points by mfiguiere on May 5, 2025 | hide | past | pdf | 37 comments
|
|
| 3218. |
ReadMe.LLM: LLM-Oriented Documentation (arxiv.org) |
|
2 points by dewley452 on May 5, 2025 | hide | past | pdf | 1 comment
|
|
| 3219. |
Multimodal Doctor-in-the-Loop: A Clinically-Guided Explainable Framework (arxiv.org) |
|
2 points by badmonster on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3220. |
CrashFixer: A crash resolution agent for the Linux kernel (arxiv.org) |
|
2 points by chrsw on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3221. |
Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions (arxiv.org) |
|
4 points by PaulHoule on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3222. |
JPEC: A Novel GNN for Competitor Retrieval in Financial Knowledge Graphs (arxiv.org) |
|
2 points by sonabinu on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3223. |
Evaluating Frontier Models for Stealth and Situational Awareness (arxiv.org) |
|
1 point by nkko on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3224. |
Llama-Nemotron: Efficient Reasoning Models (arxiv.org) |
|
7 points by nkko on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3225. |
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks (arxiv.org) |
|
2 points by EvgeniyZh on May 5, 2025 | hide | past | pdf | discuss
|
|
| 3226. |
Matrix-vector multiplication implemented in off-the-shelf DRAM for Low-Bit LLMs (arxiv.org) |
|
230 points by cpldcpu on May 4, 2025 | hide | past | pdf | 53 comments
|
|
| 3227. |
Your ViT Is Secretly an Image Segmentation Model (arxiv.org) |
|
10 points by lamename on May 4, 2025 | hide | past | pdf | discuss
|
|
| 3228. |
Chain-of-Draft surpasses CoT with only 7.6% of tokens (arxiv.org) |
|
1 point by felineflock on May 4, 2025 | hide | past | pdf | discuss
|
|
| 3229. |
Robotic Visual Instruction (arxiv.org) |
|
3 points by badmonster on May 4, 2025 | hide | past | pdf | discuss
|
|
| 3230. |
CMU TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks (arxiv.org) |
|
7 points by walterbell on May 4, 2025 | hide | past | pdf | discuss
|
|
| 3231. |
Can Transformers Reason Logically? A Study in SAT Solving (arxiv.org) |
|
1 point by sonabinu on May 4, 2025 | hide | past | pdf | discuss
|
|
| 3232. |
A Survey of AI Agent Protocols (arxiv.org) |
|
91 points by distalx on May 4, 2025 | hide | past | pdf | 63 comments
|
|
| 3233. |
Reinforcement Learning for Reasoning in LLMs with One Training Example (arxiv.org) |
|
1 point by mococa on May 3, 2025 | hide | past | pdf | 1 comment
|
|
| 3234. |
Understanding Is Compression (arxiv.org) |
|
3 points by liamdgray on May 3, 2025 | hide | past | pdf | 1 comment
|
|
| 3235. |
Stop treating `AGI' as the north-star goal of AI research (arxiv.org) |
|
46 points by todsacerdoti on May 3, 2025 | hide | past | pdf | 32 comments
|
|
| 3236. |
AI-LieDar: Examine the Trade-Off Between Utility and Truthfulness in LLM Agents (arxiv.org) |
|
1 point by msvana on May 2, 2025 | hide | past | pdf | discuss
|
|
| 3237. |
AstroAgents: MultiAgent AI for Hypothesis Generation from Mass Spectrometry Data (arxiv.org) |
|
2 points by rntn on May 2, 2025 | hide | past | pdf | discuss
|
|
| 3238. |
Step-by-step reasoning verifiers that think (arxiv.org) |
|
6 points by mkhalifa on May 2, 2025 | hide | past | pdf | 1 comment
|
|
| 3239. |
Who Gets the Callback? Generative AI and Gender Bias (arxiv.org) |
|
1 point by rntn on May 2, 2025 | hide | past | pdf | discuss
|
|
| 3240. |
Exploring the Impact of Personality Traits on Conversational Recommender Systems (arxiv.org) |
|
1 point by PaulHoule on May 2, 2025 | hide | past | pdf | discuss
|
|
|
| More |
