| 3061. |
Outcome-Based Reinforcement Learning to Predict the Future (arxiv.org) |
|
99 points by bturtel on May 27, 2025 | hide | past | pdf | 15 comments
|
|
| 3062. |
Learning to Reason Without External Rewards (arxiv.org) |
|
4 points by epipolar on May 27, 2025 | hide | past | pdf | discuss
|
|
| 3063. |
Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces (arxiv.org) |
|
16 points by andre15silva on May 27, 2025 | hide | past | pdf | discuss
|
|
| 3064. |
Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents (arxiv.org) |
|
2 points by pontiacbandit8 on May 27, 2025 | hide | past | pdf | discuss
|
|
| 3065. |
Grammars of Formal Uncertainty (arxiv.org) |
|
34 points by barthelomew on May 27, 2025 | hide | past | pdf | 5 comments
|
|
| 3066. |
ARC-NCA: Towards Developmental Solutions to the Abstraction and Reasoning Corpus (arxiv.org) |
|
1 point by jekude on May 27, 2025 | hide | past | pdf | discuss
|
|
| 3067. |
Effective Reinforcement Learning for Reasoning in Language Models (arxiv.org) |
|
4 points by obastani on May 26, 2025 | hide | past | pdf | discuss
|
|
| 3068. |
Scaling RNNs to Billions of Parameters with Zero Order (arxiv.org) |
|
7 points by fchaubard on May 26, 2025 | hide | past | pdf | 3 comments
|
|
| 3069. |
Better Zero-Shot Reasoning with Role-Play Prompting (arxiv.org) |
|
2 points by virtual_rf on May 26, 2025 | hide | past | pdf | discuss
|
|
| 3070. |
The Paradox of Prompting: Less Detail Makes AI More Human (arxiv.org) |
|
3 points by virtual_rf on May 26, 2025 | hide | past | pdf | discuss
|
|
| 3071. |
Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents (arxiv.org) |
|
4 points by nobody9999 on May 26, 2025 | hide | past | pdf | 1 comment
|
|
| 3072. |
Large Language Model-Powered Agent for C to Rust Code Translation (arxiv.org) |
|
2 points by MarcoDewey on May 25, 2025 | hide | past | pdf | discuss
|
|
| 3073. |
Interactive Post-Training for Vision-Language-Action Models (arxiv.org) |
|
4 points by badmonster on May 25, 2025 | hide | past | pdf | discuss
|
|
| 3074. |
Neural Thermodynamic Laws for Large Language Model Training (arxiv.org) |
|
6 points by anticensor on May 25, 2025 | hide | past | pdf | discuss
|
|
| 3075. |
Gen2seg: Generative Models Enable Generalizable Instance Segmentation (arxiv.org) |
|
2 points by danielmorozoff on May 25, 2025 | hide | past | pdf | discuss
|
|
| 3076. |
When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs (arxiv.org) |
|
3 points by Anon84 on May 24, 2025 | hide | past | pdf | discuss
|
|
| 3077. |
The Dangers of Browsing AI Agents (arxiv.org) |
|
2 points by wslh on May 24, 2025 | hide | past | pdf | discuss
|
|
| 3078. |
An Invitation to Neuroalgebraic Geometry (arxiv.org) |
|
2 points by IdealeZahlen on May 24, 2025 | hide | past | pdf | discuss
|
|
| 3079. |
A Consequentialist Critique of Binary Classification Evaluation Practices (arxiv.org) |
|
3 points by alexmolas on May 24, 2025 | hide | past | pdf | discuss
|
|
| 3080. |
Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens (arxiv.org) |
|
138 points by nyrikki on May 23, 2025 | hide | past | pdf | 66 comments
|
|
| 3081. |
Understanding Generative AI Capabilities in Everyday Image Editing Tasks (arxiv.org) |
|
5 points by taesiri on May 23, 2025 | hide | past | pdf | 1 comment
|
|
| 3082. |
Let Androids Dream of Electric Sheep: A Human-Like Image Implication Understand (arxiv.org) |
|
1 point by badmonster on May 23, 2025 | hide | past | pdf | discuss
|
|
| 3083. |
SDR-RDMA: Software-Defined Reliability Architecture for Planetary Scale RDMA (arxiv.org) |
|
2 points by tanelpoder on May 23, 2025 | hide | past | pdf | 1 comment
|
|
| 3084. |
The effectiveness of Large Language Models in the mechanical design domain (arxiv.org) |
|
1 point by PaulHoule on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3085. |
MMaDA: Multimodal Large Diffusion Language Models (arxiv.org) |
|
2 points by pr337h4m on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3086. |
People who use ChatGPT for writing are accurate detectors of AI-generated text (arxiv.org) |
|
1 point by speckx on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3087. |
Hierarchical-Chain-of-Generation for Complex Attributes Text-to-3D Generation (arxiv.org) |
|
2 points by PaulHoule on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3088. |
Bielik v3 Small: Technical Report (arxiv.org) |
|
1 point by PaulHoule on May 22, 2025 | hide | past | pdf | discuss
|
|
| 3089. |
Project Sid: Many-Agent Simulations Toward AI Civilization (2024) (arxiv.org) |
|
2 points by virtual_rf on May 22, 2025 | hide | past | pdf | 2 comments
|
|
| 3090. |
Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens (arxiv.org) |
|
2 points by NotInOurNames on May 22, 2025 | hide | past | pdf | discuss
|
|
|
| More |
