arXiv AI
Jul 21
LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models
arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.
FastE: Readout-Triggered Token Compression for LLM Embedding Inference
FastE is a training‑free, plug‑and‑play method that compresses token prefixes in large language model (LLM) embedding inference. It uses a shared fixed threshold on batch‑mean readout‑prefix alignment to decide when to compress and ranks prefix states by readout attention scores to keep the most important ones. Experiments on Qwen3‑Embedding models show that FastE can cut decoder‑backbone FLOPs by over 40% while preserving more than 99% of the original ranking quality across multiple benchmarks and tasks.
Related stories
arXiv AI
Jul 8
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
arXiv:2607. 06523v1 Announce Type: new Abstract: Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation.
arXiv AI
Jul 21
SelKV: Selective KV Cache Merging with Per-Token Merge-or-Drop and Attention Compensation
arXiv:2607. 16213v1 Announce Type: new Abstract: Large Language Models (LLMs) generate text autoregressively, relying on a key-value (KV) cache whose memory footprint grows linearly with context length, creating a major bottleneck.
arXiv AI
Jun 9
End-to-End Context Compression at Scale
arXiv:2606. 09659v1 Announce Type: cross Abstract: Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length.
arXiv AI
Jul 7
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
arXiv:2605. 25475v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference.
arXiv Computer Vision
1d ago
Layer-Aware Position Embeddings for Visual Token Pruning in Multimodal Large Language Models
arXiv:2609.23715v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) incur substantial computational overhead due to the reliance on hundreds of visual tokens to represent images....
arXiv Machine Learning
Aug 31
Accelerating LLM Inference via Vector Index Based Output Embeddings
The paper proposes replacing dense output projection in large language models with an HNSW-based vector index to perform maximum inner product search over token embeddings. This approach reduces memory bandwidth usage by retrieving only a small set of high-scoring tokens and can be integrated into existing decoding pipelines via sparse logits scattering. Experiments on Gemma 3, Llama 3.2, and Qwen 3 show up to 82% speed‑up in batch‑size‑one decoding while maintaining generation quality.
arXiv Machine Learning
Aug 26
PuzzleKV: Page-Wise Low-Rank Decomposition for KV Cache Compression
arXiv:2608.23843v1 Announce Type: new Abstract: Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compressio...
Hugging Face Trending Papers
Jun 24
BitNet Text Embeddings
LLM-based text embedders have substantially improved retrieval and semantic representation quality, but their deployment remains costly: large backbone models slow down embedding inference, while high-dimensional full-precision embeddings impose substantial storage and bandwidth overhead on large-scale indexes. In this paper, we present BITEMBED, an extreme low-bit framework for LLM-based text embedding that jointly targets encoding efficiency and vector storage.
arXiv Computation and Language
2d ago
VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
arXiv AI
Sep 10
Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models
The paper introduces K-Token Merging, a latent-space compression method that merges each contiguous block of K token embeddings into a single embedding using a lightweight encoder. The compressed sequence is then processed by a LoRA-adapted large language model, while generation continues in the original vocabulary. Experiments on tasks such as structural reasoning, sentiment classification, and code editing demonstrate that K-Token Merging achieves up to 75% input length reduction with minimal performance loss, placing it on the Pareto frontier of performance versus compression.
arXiv AI
Aug 25
KVBoost: Chunk-Level Key-Value Cache Reuse with Deviation-Guided Recomputation for Efficient Large Language Model Inference
arXiv:2608.21362v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) incur high prefill latency because key-value (KV) tensors must be recomputed for each request. Existing...