| 3541. |
L1: Controlling How Long a Reasoning Model Thinks with Reinforcement Learning (arxiv.org) |
|
2 points by papers2092 on Mar 7, 2025 | hide | past | pdf | discuss
|
|
| 3542. |
Hot: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs (arxiv.org) |
|
4 points by taesiri on Mar 7, 2025 | hide | past | pdf | 1 comment
|
|
| 3543. |
Computation-Aware ControlNet with Dynamic Router for Text-to-Image Generation (arxiv.org) |
|
3 points by jinqueeny on Mar 7, 2025 | hide | past | pdf | discuss
|
|
| 3544. |
Ladder: Self-improving LLMs through recursive problem decomposition (arxiv.org) |
|
370 points by fofoz on Mar 7, 2025 | hide | past | pdf | 110 comments
|
|
| 3545. |
Hallucinations are inevitable but statistically negligible (arxiv.org) |
|
2 points by pash on Mar 6, 2025 | hide | past | pdf | discuss
|
|
| 3546. |
Large Models Aren't Physical Reasoners (arxiv.org) |
|
3 points by australium on Mar 6, 2025 | hide | past | pdf | discuss
|
|
| 3547. |
Evaluating Intelligence via Trial and Error (arxiv.org) |
|
1 point by hunglee2 on Mar 6, 2025 | hide | past | pdf | discuss
|
|
| 3548. |
Spark-TTS: Text-2-Speech Model Single-Stream Decoupled Tokens [pdf] (arxiv.org) |
|
78 points by bilekas on Mar 6, 2025 | hide | past | pdf | 6 comments
|
|
| 3549. |
Benchmark on Multi-Embodiment Intelligence Normative Data for Robot Manipulation (arxiv.org) |
|
1 point by Open_X_humanoid on Mar 6, 2025 | hide | past | pdf | discuss
|
|
| 3550. |
Towards Understanding Distilled Reasoning Models: A Representational Approach (arxiv.org) |
|
3 points by bearseascape on Mar 6, 2025 | hide | past | pdf | discuss
|
|
| 3551. |
Cognitive Behaviors That Enable Self-Improving Reasoners (arxiv.org) |
|
279 points by delifue on Mar 6, 2025 | hide | past | pdf | 103 comments
|
|
| 3552. |
16-Bit to 1-Bit: Visual KV Cache Quantization for Efficient Multimodal LLMs (arxiv.org) |
|
87 points by PaulHoule on Mar 5, 2025 | hide | past | pdf | 1 comment
|
|
| 3553. |
Evolutionary Multi-Agent Reinforcement Learning in Group Social Dilemmas (arxiv.org) |
|
2 points by rntn on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3554. |
Evaluating Intelligence via Trial and Error (arxiv.org) |
|
2 points by rntn on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3555. |
Training LLMs with Order-Centric Augmentation (arxiv.org) |
|
2 points by musha68k on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3556. |
Coderag-Bench: Can Retrieval Augment Code Generation? (arxiv.org) |
|
1 point by knes on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3557. |
Learning Quiet Walking for a Small Home Robot (arxiv.org) |
|
1 point by Tomte on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3558. |
Convolutional Multi-Hybrid Language Models (arxiv.org) |
|
2 points by zymrael_ on Mar 5, 2025 | hide | past | pdf | discuss
|
|
| 3559. |
Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs (arxiv.org) |
|
1 point by wslh on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3560. |
HumT DumT: Measuring and controlling human-like language in LLMs (arxiv.org) |
|
1 point by PaulHoule on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3561. |
Translating natural language to first-order logic for logical fallacy detection (arxiv.org) |
|
258 points by ColinWright on Mar 4, 2025 | hide | past | pdf | 143 comments
|
|
| 3562. |
Chain of Draft: Thinking Faster by Writing Less (arxiv.org) |
|
4 points by coloneltcb on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3563. |
How Well Do LLMs Compress Their Own Chain-of-Thought? (arxiv.org) |
|
1 point by Jimmc414 on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3564. |
Neuro-Symbolic Semantic Slam with Hierarchically Categorical Gaussian Splatting (arxiv.org) |
|
2 points by PaulHoule on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3565. |
Training LLMs with MXFP4 (arxiv.org) |
|
2 points by nrekjydsf45 on Mar 4, 2025 | hide | past | pdf | discuss
|
|
| 3566. |
Order Doesn’t Matter, But Reasoning Does (arxiv.org) |
|
14 points by spaintech on Mar 3, 2025 | hide | past | pdf | 16 comments
|
|
| 3567. |
Art: Anonymous Region Transformer (arxiv.org) |
|
2 points by geox on Mar 3, 2025 | hide | past | pdf | discuss
|
|
| 3568. |
Cautious Optimizers: Improving Training with One Line of Code (arxiv.org) |
|
66 points by tosh on Mar 3, 2025 | hide | past | pdf | 2 comments
|
|
| 3569. |
Transformers Learn to Implement Multistep Gradient Descent with Chain of Thought (arxiv.org) |
|
1 point by bearseascape on Mar 3, 2025 | hide | past | pdf | discuss
|
|
| 3570. |
Flash Interpretability: Decoding Specialised Feature Neurons in LLM (arxiv.org) |
|
1 point by mococa on Mar 3, 2025 | hide | past | pdf | discuss
|
|
|
| More |
