Published onDecember 6, 2025Reinforcement Learning for Long-Horizon Multi-Turn Search AgentsPaperLLMWorkshopRAGAgentsReinforcementLearningRLRead more →
Published onNovember 26, 2025Evolving ReasoningLLMSAM3SAM3D-ObjectSAM3D-BodyReasoningEvolutionReinforcement-LearningGRPODistillationOn-PolicyRead more →
Published onNovember 22, 2025DevFest SG Talk: Lessons from Reinforcement LearningLLMReinforcement-LearningPromptingFineTuningSFTDevFestRead more →
Published onOctober 15, 2025Neural Assets and World ModelsTransformersStableDiffusionDallENanoBananaVOYAGERMinecraftTinyWorldsGENIERead more →
Published onSeptember 25, 2025IPhO Gold using Agentic GeminiLLMTransformersAgentsIPhOPhysicsPhysicsOlympiadGeminiRead more →
Published onAugust 27, 2025Agent Efficiency, Memory and ConfidenceLLMTransformersAgentsEfficiencyMemoryARPODeepThinkRead more →
Published onJuly 16, 2025A Reasoning-Based Approach to Cryptic Crossword Clue SolvingPaperLLMReasoningFormalisationCryptic-CrosswordsRead more →
Published onJuly 3, 2025GPU Kernel Scientist : An LLM-Driven Framework for Iterative Kernel OptimizationPaperLLMGPUAMDCUDAGeminiWorkshopRead more →
Published onJune 19, 2025Self-Improving AgentsLLMTransformersDarwinGodelMachinesDarwinGoedelMachinesGenetic-ProgrammingGenetic-AlgorithmsGPU-Kernel-ScientistGPUAMDDSPyRead more →
Published onMay 22, 2025Evolving GPU KernelsLLMTransformersAlphaEvolveGenetic-ProgrammingGenetic-AlgorithmsGPUAMDRead more →