Build Loop · Decide which papers become startups. · Today's queue.
BUILD-LOOP··SORT:·CLUSTER:·
18 buildableof 130 papers·15 await proof·87 with code
/
Filters
Cluster
130 papers
#PAPERCLUSTERDATESCORE
1OpenSkill: Open-World Self-Evolution for LLM AgentsAgents5d71.6237
2Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision TransformersAI Interpretability5d71.4536
3Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training StrategyUncategorized4d69.8836
4Watch, Remember, Reason: Human-View Video Understanding with MLLMsUncategorized4d69.4883
5HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They RuleLegal AI5d69.3836
6Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic AlignmentUncategorized4d69.2836
7OpenHalDet: A Unified Benchmark for Hallucination Detection across Diverse Generation ScenariosUncategorized4d69.1836
8MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language ModelsUncategorized4d68.0836
9PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper StreamsUncategorized4d67.3767
10DyCon: Dynamic Reasoning Control via Evolving Difficulty ModelingUncategorized4d67.0772
11Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research LifecycleUncategorized4d66.9901
12dots.tts Technical ReportUncategorized4d64.27
13GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution DetectionUncategorized4d64.0165
14SS-TPT: Stability and Suitability-Guided Test-Time Prompt Tuning for Adversarially Robust Vision-Language ModelsUncategorized4d63.4665
15Accelerated Fourier SAT (AFSAT): Fully Realising a GPU-based Symmetric Pseudo-Boolean SAT SolverSAT Solvers5d63.2336
16The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical ReasoningUncategorized4d60.8536
17Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation ModulationUncategorized4d60.4001
18ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM ReasoningUncategorized4d60.21
19Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement LearningUncategorized4d60.0836
20UrduMMLU: A Massive Multitask Benchmark for Urdu Language UnderstandingUncategorized4d60.0836
21EgoPressDiff: Multimodal Video Diffusion for Egocentric UV-Domain Hand-Pressure EstimationUncategorized4d59.96
22DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded ReasoningUncategorized4d59.47
23Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized TestsUncategorized4d59.0493
24FIGMA: Towards FIne-Grained Music retrievAlMusic Retrieval5d58.91
25FreeAnimate: Training-Free Human Image Animation with Preview-Guided DenoisingUncategorized4d57.61
26What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos?Robotics Manipulation5d55.57
27AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor ManipulationRobotics5d55.57
28MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval MechanismVideo Processing and Analysis4d55.57
29Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event LocalizationUncategorized4d55.57
30DaX: Learning General Pathology Representations Across ScalesUncategorized4d55.57