Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 10 days ago • 66
AutoMem: Automated Learning of Memory as a Cognitive Skill Paper • 2607.01224 • Published 12 days ago • 19
FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation Paper • 2606.24876 • Published 20 days ago • 24
KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks Paper • 2606.03458 • Published Jun 2 • 67
SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers Paper • 2605.22668 • Published May 21 • 41
Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis Paper • 2605.18451 • Published May 18 • 41
SVGS: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors Paper • 2411.18966 • Published May 4 • 9
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks Paper • 2604.08539 • Published Apr 9 • 51
MARS: Enabling Autoregressive Models Multi-Token Generation Paper • 2604.07023 • Published Apr 8 • 38
Experience Transfer for Multimodal LLM Agents in Minecraft Game Paper • 2604.05533 • Published Apr 7 • 16
360Anything: Geometry-Free Lifting of Images and Videos to 360° Paper • 2601.16192 • Published Jan 22 • 9