| 2761. |
Hi-SQL: Optimizing Text-to-SQL Systems Through Dynamic Hint Integration (arxiv.org) |
|
1 point by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2762. |
MemOS: A Memory OS for AI System (arxiv.org) |
|
3 points by handfuloflight on Jul 9, 2025 | hide | past | pdf | 2 comments
|
|
| 2763. |
The Cost of an Image: The Energy Consumption of AI Image Generation (arxiv.org) |
|
6 points by GodelInTheShell on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2764. |
Can LLMs Replace Humans During Code Chunking? (arxiv.org) |
|
1 point by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2765. |
How to Train a Model on a Cheap Cluster Using Block Coordinate Descent (arxiv.org) |
|
2 points by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2766. |
Empirical Evaluation of Large Language Models in Automated Program Repair (arxiv.org) |
|
5 points by Bluestein on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2767. |
UCD: Unlearning in LLMs via Contrastive Decoding (arxiv.org) |
|
2 points by PaulHoule on Jul 9, 2025 | hide | past | pdf | discuss
|
|
| 2768. |
Paper: Disambiguation-Centric Finetuning Makes Tool-Calling LLMs More Realistic (arxiv.org) |
|
2 points by ashutosh1919 on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2769. |
Why Do Some Language Models Fake Alignment While Others Don't? (arxiv.org) |
|
3 points by mfiguiere on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2770. |
Design Patterns for Securing LLM Agents Against Prompt Injections (arxiv.org) |
|
3 points by rbanffy on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2771. |
InfoFlood: Jailbreaking Large Language Models with Information Overload (arxiv.org) |
|
2 points by rswerve on Jul 8, 2025 | hide | past | pdf | 1 comment
|
|
| 2772. |
X-Master as Foundation: Can We Lead on Humanity's Last Exam? (arxiv.org) |
|
1 point by Leary on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2773. |
Cats Confuse Reasoning LLM – Adversarial Triggers for Reasoning Models (arxiv.org) |
|
1 point by tfpgh on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2774. |
Interpreting Large Language Model's Personality Through Critical Event Analysis (arxiv.org) |
|
2 points by PaulHoule on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2775. |
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Gen (arxiv.org) |
|
7 points by jlaneve on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2776. |
Strategic Intelligence in Large Language Models: Evidence from Evolutionary GT (arxiv.org) |
|
2 points by psychoslave on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2777. |
Energy-Based Transformers Are Scalable Learners and Thinkers (arxiv.org) |
|
5 points by jonbaer on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2778. |
Measuring AI Ability to Complete Long Tasks (arxiv.org) |
|
3 points by sonabinu on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2779. |
Reading Smiles: Proxy Bias in Foundation Models for Facial Emotion Recognition (arxiv.org) |
|
2 points by PaulHoule on Jul 8, 2025 | hide | past | pdf | discuss
|
|
| 2780. |
Frustratingly Simple Retrieval for Challenging, Reasoning-Intensive Benchmarks (arxiv.org) |
|
2 points by amirkabbara on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2781. |
Query Agnostic Adversarial Triggers for Reasoning Models (arxiv.org) |
|
5 points by layer8 on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2782. |
Because We Have LLMs, We Can and Should Pursue Agentic Interpretability (arxiv.org) |
|
4 points by favoboa on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2783. |
AsyncFlow: An Asynchronous Streaming RL Framework for LLM Post-Training (arxiv.org) |
|
4 points by robertnishihara on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2784. |
Mercury: Ultra-fast language models based on diffusion (arxiv.org) |
|
576 points by PaulHoule on Jul 7, 2025 | hide | past | pdf | 242 comments
|
|
| 2785. |
Sequential Diagnosis with Language Models (arxiv.org) |
|
4 points by herrherr on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2786. |
Segmentation and Representation Trade-Offs in Chemistry-Aware RAG (arxiv.org) |
|
2 points by PaulHoule on Jul 7, 2025 | hide | past | pdf | discuss
|
|
| 2787. |
LLMs should not replace therapists (arxiv.org) |
|
303 points by layer8 on Jul 6, 2025 | hide | past | pdf | 417 comments
|
|
| 2788. |
Primitive-Based Generation of Controllable and Editable 3D Semantic Scenes (arxiv.org) |
|
3 points by PaulHoule on Jul 6, 2025 | hide | past | pdf | discuss
|
|
| 2789. |
Establishing Best Practices for Building Rigorous Agentic Benchmarks (arxiv.org) |
|
4 points by frontfor on Jul 6, 2025 | hide | past | pdf | discuss
|
|
| 2790. |
Fast and Simplex: 2-Simplicial Attention in Triton (arxiv.org) |
|
3 points by anythingworks on Jul 5, 2025 | hide | past | pdf | discuss
|
|
|
| More |
