| Unshackling Context Length: An Efficient Selective Attention Approach through Query-Key Compression | Feb 20, 2025 | 8k | —Unverified | 0 |
| ParallelComp: Parallel Long-Context Compressor for Length Extrapolation | Feb 20, 2025 | 4k8k | —Unverified | 0 |
| CopySpec: Accelerating LLMs with Speculative Copy-and-Paste Without Compromising Quality | Feb 13, 2025 | 8kGPU | CodeCode Available | 0 |
| GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity? | Feb 7, 2025 | 8kInformation Retrieval | CodeCode Available | 2 |
| BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics | Jan 31, 2025 | 8kImage Generation | —Unverified | 0 |
| State Stream Transformer (SST) : Emergent Metacognitive Behaviours Through Latent State Persistence | Jan 30, 2025 | 8kARC | —Unverified | 0 |
| Directing Mamba to Complex Textures: An Efficient Texture-Aware State Space Model for Image Restoration | Jan 27, 2025 | 4k8k | —Unverified | 0 |
| LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation | Jan 9, 2025 | 2k8k | —Unverified | 0 |
| Towards High-fidelity 3D Talking Avatar with Personalized Dynamic Texture | Jan 1, 2025 | 3D Face Animation8k | —Unverified | 0 |
| CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up | Dec 20, 2024 | 8kGPU | CodeCode Available | 3 |
