S*: Test Time Scaling for Code Generation
Paper
•
2502.14382
•
Published
•
49
Asankhaya Sharma
codelion
AI & ML interests
AI/ML, Dev Tools and Application Security
Recent Activity
upvoted
a
paper
2 days ago
S*: Test Time Scaling for Code Generation
updated
a Space
3 days ago
codelion/markdownPDF
liked
a Space
3 days ago
codelion/markdownPDF
Organizations
codelion's activity
upvoted
a
paper
2 days ago
updated
a
Space
3 days ago
liked
a
Space
3 days ago
published
a
Space
3 days ago
upvoted
a
collection
4 days ago
upvoted
2
papers
5 days ago
updated
a
Space
5 days ago
liked
a
Space
5 days ago
published
a
Space
5 days ago
updated
a
dataset
6 days ago
We have also had good success applying tts more broadly at a diverse set of tasks in optillm - https://github.com/codelion/optillm
commented on
What is test-time compute and how to scale it?
6 days ago
Great survey, if you want to play around with many of the these techniques you can do so in our open-source optimizing inference proxy optillm - https://github.com/codelion/optillm
upvoted
an
article
6 days ago
Article
What is test-time compute and how to scale it?
By
and 1 other
•
•
39
reacted to
Kseniase's
post with 🚀🔥
6 days ago
Post
3115
8 New Applications of Test-Time Scaling
We've noticed a huge interest in test-time scaling (TTS), so we decided to explore this concept further. Test-time compute (TTC) refers to the amount of computational power used by an AI model when generating a response. Many researchers are now focused on scaling TTC, as it enables slow, deep "thinking" and step-by-step reasoning, which improves overall models' performance.
Here are 8 fresh studies on test-time scaling:
1. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach (2502.05171)
Introduces an LM that scales TTC by reasoning in latent space instead of generating more tokens with no special training. Here, a recurrent block to processes information iteratively.
2. Generating Symbolic World Models via Test-time Scaling of Large Language Models (2502.04728)
Shows how TTS is applied to enhance model's Planning Domain Definition Language (PDDL) reasoning capabilities, which can be used to generate a symbolic world model.
3. Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling (2502.06703)
Analyzes optimal TTS strategies and shows how small models can outperform much larger ones.
4. Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis (2502.04128)
Shows how TTS improves expressiveness, timbre consistency and accuracy in speech synthesis with Llasa framework. It also dives into benefits of scaling train-time compute.
5. Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning (2502.07154)
Suggests a modified training loss for better reasoning of LLMs when scaling TTC.
6. Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures (2502.05078)
Unifies the strengths of chain, tree, and graph paradigms into one framework that expands reasoning only on necessary subproblems.
7. Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification (2502.01839)
Explores scaling trends of self-verification and how to improve its capabilities with TTC.
8. CodeMonkeys: Scaling Test-Time Compute for Software Engineering (2501.14723)
Explores how scaling serial compute (iterations) and parallel compute (trajectories), can improve accuracy in real-world software engineering issues.
Also, explore our article about TTS for more -> https://huggingface.co/blog/Kseniase/testtimecompute
We've noticed a huge interest in test-time scaling (TTS), so we decided to explore this concept further. Test-time compute (TTC) refers to the amount of computational power used by an AI model when generating a response. Many researchers are now focused on scaling TTC, as it enables slow, deep "thinking" and step-by-step reasoning, which improves overall models' performance.
Here are 8 fresh studies on test-time scaling:
1. Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach (2502.05171)
Introduces an LM that scales TTC by reasoning in latent space instead of generating more tokens with no special training. Here, a recurrent block to processes information iteratively.
2. Generating Symbolic World Models via Test-time Scaling of Large Language Models (2502.04728)
Shows how TTS is applied to enhance model's Planning Domain Definition Language (PDDL) reasoning capabilities, which can be used to generate a symbolic world model.
3. Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling (2502.06703)
Analyzes optimal TTS strategies and shows how small models can outperform much larger ones.
4. Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis (2502.04128)
Shows how TTS improves expressiveness, timbre consistency and accuracy in speech synthesis with Llasa framework. It also dives into benefits of scaling train-time compute.
5. Rethinking Fine-Tuning when Scaling Test-Time Compute: Limiting Confidence Improves Mathematical Reasoning (2502.07154)
Suggests a modified training loss for better reasoning of LLMs when scaling TTC.
6. Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures (2502.05078)
Unifies the strengths of chain, tree, and graph paradigms into one framework that expands reasoning only on necessary subproblems.
7. Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification (2502.01839)
Explores scaling trends of self-verification and how to improve its capabilities with TTC.
8. CodeMonkeys: Scaling Test-Time Compute for Software Engineering (2501.14723)
Explores how scaling serial compute (iterations) and parallel compute (trajectories), can improve accuracy in real-world software engineering issues.
Also, explore our article about TTS for more -> https://huggingface.co/blog/Kseniase/testtimecompute
-
- 1 reply
liked
a
dataset
7 days ago
updated
2
datasets
7 days ago