LoopVAE introduces a recurrent depth architecture that reuses a scale‑ and loop‑conditioned core across different spatial scales while keeping resolution‑changing transitions separate. The four‑block core applies 28 block operations per encoder or decoder, enabling a 29M‑parameter convolutional model to achieve 0.28 rFID and 32.54 dB PSNR on ImageNet‑256 with roughly 65% fewer parameters than comparable VAEs. Experiments with both convolutional and Transformer operators, as well as ablations on parameter sharing, demonstrate competitive image quality metrics and reveal how targeted loop interventions and truncation affect reconstruction quality and computational trade‑offs.
arXiv:2609.35232v2 Announce Type: replace-cross Abstract: Visual-token compression is effective for improving the efficiency of vision-language models, but under extreme compression budgets, token pr...
arXiv:2609.39924v1 Announce Type: cross Abstract: Vision-language models face a fundamental scaling bottleneck: the number of visual tokens grows with both temporal duration and spatial resolution, m...
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.
The paper introduces Gated Recurrent Transformers, a depth‑sharing architecture that brackets a single shared core with fixed prelude and coda blocks and uses a lightweight projection and element‑wise update gate to modulate recurrent updates. This design allows functional specialization across recurrences while reducing memory footprint. Experiments show that, under equal FLOPs or parameter budgets, the recurrent model matches or surpasses deeper GPT‑2 Small baselines, achieving similar or better accuracy with fewer parameters and lower peak decoding memory.
arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.
arXiv:2607. 26596v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual understanding within a unified transformer architecture.
arXiv:2608.15062v3 Announce Type: replace-cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layer...
VisionWeave introduces elastic visual representation weaving, a native capability for multimodal large language models that learns where and at what granularity to encode visual information. The method combines a gated spatial pooler for coarse representations with a granularity router that allocates content‑adaptive token usage, trained end‑to‑end on large‑scale data. Experiments on Qwen3.5‑4B and Qwen3.8‑27B show that VisionWeave can save 43.0% of tokens while preserving 98.9% of performance across eight benchmarks, and delivers significant throughput gains and latency reductions when deployed on the SGLang serving engine.
The paper introduces PACE, a Pareto‑adaptive compression framework designed for native multimodal large language models (MLLMs) that directly tokenize pixel patches without external vision encoders. By analyzing token discriminability and heterogeneous redundancy across spatial dimensions, PACE decomposes attention into height‑ and width‑specific saliency maps and applies a Pareto‑optimization strategy to allocate token budgets, achieving near‑lossless performance with only 25‑50% of visual tokens and more than 2× FLOP savings. Experiments demonstrate that PACE not only preserves but sometimes improves benchmark results compared to existing ViT‑based compression methods.
arXiv:2607. 25527v1 Announce Type: cross Abstract: Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities.
PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.
The paper introduces LoopCD, a training‑free contrastive decoding framework that improves token selection in Loop‑Transformer models by comparing the final prediction with earlier recurrent passes. LoopCD operates either in logit space (LoopCD‑Logits) with a single extra output pass or in hidden‑state space (LoopCD‑Hidden) with no output overhead. Across multiple looped Transformer families, LoopCD yields significant performance gains—raising pass@1 scores on tasks such as AIME 2024 and HumanEval—while enabling a reduction in the number of recurrent loops and a corresponding decrease in inference FLOPs.