Build Loop

#PAPERCLUSTERDATESCORE

1EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving AgentsAI Adaptation Systems1d59
2Piper: A Programmable Distributed Training SystemDistributed Systems1d40.77
3A Unifying Lens on Supervised Fine-Tuning Through Target Distribution DesignResearch Methodologies1d35.77
4Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum RepresentationsUncategorized1d33.18
5Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and TranslationUncategorized1d32.43
6Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial GamesUncategorized1d32.43
7FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language modelUncategorized1d32.43
8A History-Aware Visually Grounded Critic for Computer Use AgentsUncategorized1d32.4
9Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA EncodingUncategorized1d31.99
10From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMsUncategorized1d31.88
11++nnU-Net: Scaling nnU-Net with Prefix-Based Data AugmentationUncategorized1d31.88
12The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent MisalignmentUncategorized1d31.55
13LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint ImaginationUncategorized1d31.09
14One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QAUncategorized1d31
15The Role of Feedback Alignment in Self-DistillationAI/ML Techniques1d28.07
16Flaws in the LLM Automation NarrativeAI Ethics and Evaluation1d27.17
17Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual ArtifactsUncategorized1d24.12
18Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional FieldsUncategorized1d23.81
19Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?Uncategorized1d23.26
20Machine Learning Methods for Studying Latent Neural Activity DynamicsUncategorized1d23.15
21ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level CombinatoricsUncategorized1d23.15
22Role-Agent: Bootstrapping LLM Agents via Dual-Role EvolutionUncategorized1d23.15
23T1-Bench: Benchmarking Multi-Scenario Agents in Real-World DomainsUncategorized1d23.15
24Test-Time Gradient Guidance of Flow Policies in Reinforcement LearningUncategorized1d23.15
25CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMsUncategorized1d23.15
26Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM ReasoningUncategorized1d23.12
27Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion PoliciesUncategorized1d23.11
28Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise EvaluationUncategorized1d22.81
29Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease PredictionUncategorized1d22.71
30Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement LearningUncategorized1d22.71

Select a paper from the list to view details.

Build Loop · Decide which papers become startups. · Today's queue.