Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling
Paper • 2512.23959 • Published • 112
kodjo
smartmeouh
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning upvoted a paper 1 day ago
R-Zero: Self-Evolving Reasoning LLM from Zero DataOrganizations
None yet
upvoted 4
papers 1 day ago
upvoted 4
papers 2 days ago
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
Paper • 2511.21689 • Published • 129
TiDAR: Think in Diffusion, Talk in Autoregression
Paper • 2511.08923 • Published • 130
LongLive: Real-time Interactive Long Video Generation
Paper • 2509.22622 • Published • 190
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 235
upvoted 9
papers 9 days ago
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 34
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Paper • 2601.05175 • Published • 38
The Path Not Taken: RLVR Provably Learns Off the Principals
Paper • 2511.08567 • Published • 37
VGGT: Visual Geometry Grounded Transformer
Paper • 2503.11651 • Published • 40
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Paper • 2512.07802 • Published • 47
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
Paper • 2509.25760 • Published • 56
SAM 3D: 3Dfy Anything in Images
Paper • 2511.16624 • Published • 117
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 138
DINOv3
Paper • 2508.10104 • Published • 312
upvoted 3
papers 7 months ago
AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
Paper • 2511.23475 • Published • 43
DiP: Taming Diffusion Models in Pixel Space
Paper • 2511.18822 • Published • 30
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
Paper • 2511.22663 • Published • 29