AMO-Bench- Large Language Models Still Struggle in High School Math Competitions
A presentation about aMO-Bench- Large Language Models Still Struggle in High School Math Competitions.
TechnologyManuscripts
41 resources
AMemGym- Interactive Memory Benchmarking for Assistants in Long-horizon Conversations
A presentation about aMemGym- Interactive Memory Benchmarking for Assistants in Long-horizon Conversations.
Technology
Implementing Interactive Indoor Maps with MapLibre and IMDF
A presentation about implementing Interactive Indoor Maps with MapLibre and IMDF.
Technology
Externalization in LLM Agents- A Unified Review of Memory, Skills, Protocols and Harness Engineering
A presentation about externalization in LLM Agents- A Unified Review of Memory, Skills, Protocols and Harness Engineering.
Technology
Process Reward Models- Math to Code
A presentation about process Reward Models- Math to Code.
Technology
Scaling and Transferability of Annealing Strategies in Large Language Model Training
A presentation about scaling and Transferability of Annealing Strategies in Large Language Model Training.
Technology
SRFT- A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
A presentation about sRFT- A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning.
Technology
ViPER- Empowering the Self-Evolution of Visual Perception Abilities in VisionLanguage Models
A presentation about viPER- Empowering the Self-Evolution of Visual Perception Abilities in VisionLanguage Models.
Technology
SAE as a Crystal Ball- Interpretable Features Predict Cross-domain Transferability of LLMs without Training
A presentation about sAE as a Crystal Ball- Interpretable Features Predict Cross-domain Transferability of LLMs without Training.
Technology