Test-Time Scaling of Reasoning Models for Machine Translation
Paper
β’
2510.06471
β’
Published
AI & ML interests
At the University of Helsinki, we focus on: - NLP for morphologically-rich languages - Cross-lingual NLP - NLP in the humanities
Recent Activity
View all activity
Zihao-LiΒ
authored
a
paper
6 days ago
Zihao-LiΒ
updated
a
dataset
10 days ago
Zihao-LiΒ
authored
6
papers
2 months ago
EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models
Paper
β’
2409.17892
β’
Published
β’
2
GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models
Paper
β’
2504.04155
β’
Published
β’
1
Rethinking Multilingual Continual Pretraining: Data Mixing for Adapting LLMs Across Languages and Resources
Paper
β’
2504.04152
β’
Published
β’
1
Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data
Paper
β’
2506.00469
β’
Published
β’
3
A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives
Paper
β’
2407.15489
β’
Published
Scaling Low-Resource MT via Synthetic Data Generation with LLMs
Paper
β’
2505.14423
β’
Published
β’
1
albertvillanovaΒ
posted
an
update
3 months ago
Post
3745
Latest smolagents release supports GPT-5: build agents that think, plan, and act.
β‘ Upgrade now and put GPT-5 to work!
β‘ Upgrade now and put GPT-5 to work!
albertvillanovaΒ
posted
an
update
3 months ago
Post
568
π smolagents v1.21.0 is here!
Now with improved safety in the local Python executor: dunder calls are blocked!
β οΈ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
β¨ Many bug fixes: more reliable code.
π https://github.com/huggingface/smolagents/releases/tag/v1.21.0
Now with improved safety in the local Python executor: dunder calls are blocked!
β οΈ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
β¨ Many bug fixes: more reliable code.
π https://github.com/huggingface/smolagents/releases/tag/v1.21.0
albertvillanovaΒ
posted
an
update
4 months ago
Post
710
π New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
π§ Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
β Isolated execution = no host access
β No need for Python on the user's machine
β Safer evaluation of arbitrary code
β Compatible with serverless / edge agent workloads
β Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. π‘
π‘ We're inviting the open-source community to help evolve this executor:
β’ Tackle more advanced Python features
β’ Expand compatibility
β’ Add test coverage
β’ Shape the next-gen secure agent runtime
π Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together π§ βοΈ
π https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
π§ Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
β Isolated execution = no host access
β No need for Python on the user's machine
β Safer evaluation of arbitrary code
β Compatible with serverless / edge agent workloads
β Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. π‘
π‘ We're inviting the open-source community to help evolve this executor:
β’ Tackle more advanced Python features
β’ Expand compatibility
β’ Add test coverage
β’ Shape the next-gen secure agent runtime
π Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together π§ βοΈ
π https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
albertvillanovaΒ
posted
an
update
4 months ago
Post
1757
π SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
π§ Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
π₯οΈ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
π Streaming Refactor
- Streaming event aggregation moved off the Model class
- β‘οΈ Better architecture & maintainability
π¦ Output Tracking
- CodeAgent outputs are now stored in ActionStep
- β More visibility and structure to agent decisions
π Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
π Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
π Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
π¬ Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
π§ Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
π₯οΈ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
π Streaming Refactor
- Streaming event aggregation moved off the Model class
- β‘οΈ Better architecture & maintainability
π¦ Output Tracking
- CodeAgent outputs are now stored in ActionStep
- β More visibility and structure to agent decisions
π Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
π Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
π Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
π¬ Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace
hengyu-luoΒ
authored
a
paper
5 months ago
tiedemanΒ
authored
a
paper
5 months ago
jisxΒ
authored
6
papers
5 months ago
Towards Interpretable Mental Health Analysis with Large Language Models
Paper
β’
2304.03347
β’
Published
A Survey on Knowledge Graphs: Representation, Acquisition and Applications
Paper
β’
2002.00388
β’
Published
β’
1
Suicidal Ideation and Mental Disorder Detection with Attentive Relation Networks
Paper
β’
2004.07601
β’
Published
A New Massive Multilingual Dataset for High-Performance Language Technologies
Paper
β’
2403.14009
β’
Published
β’
1
Lucky 52: How Many Languages Are Needed to Instruction Fine-Tune Large Language Models?
Paper
β’
2404.04850
β’
Published
GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models
Paper
β’
2504.04155
β’
Published
β’
1