arXiv:2606. 02737v1 Announce Type: cross Abstract: Dense retrieval models exhibit positional bias: retrieval effectiveness degrades when relevant information appears later in a passage (Zeng et al.
arXiv:2605. 11374v5 Announce Type: replace Abstract: Test-time compute is widely believed to benefit only large reasoning models, leaving small models with nothing to gain.
arXiv:2606. 30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query.
arXiv:2606. 28560v1 Announce Type: cross Abstract: We study sparse self-attention in which each query attends to a dense local window plus a set of Fibonacci-spaced offsets, with a per-layer scalar alpha that compresses or expands the spacing.
arXiv:2606. 29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in cold-start and long-tail regimes.
arXiv:2607. 18785v2 Announce Type: replace Abstract: As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution.
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:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.
arXiv:2607. 09052v1 Announce Type: new Abstract: Block sparse attention is a hardware friendly way to alleviate the key-value (KV) cache read bottleneck in large language models (LLMs).
arXiv:2606. 01294v1 Announce Type: cross Abstract: Linear attention reduces the quadratic cost of softmax attention by maintaining a recurrent fast-weight state, but it consistently lags on in-context retrieval and long-context tasks.
arXiv:2607. 02104v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as cheap, scalable judges that compare candidate outputs pairwise -- to rank responses, select models, or triage papers.
arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.