Search: “retrieval”

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr

arXiv:2610.07385v1 Announce Type: new Abstract: Fine-tuning vision-language models (VLMs) is typically evaluated at a single downstream checkpoint, obscuring whether a semantic capability was never ac

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

The team has announced the launch of **LlamaIndex**, an open‑source information‑retrieval library, with its main site listed at **llamaindex.ai**. The announcement was shared on Twitter by Imaan Sulta

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside

arXiv:2610.15033v1 Announce Type: cross Abstract: Generative search engines such as ChatGPT, Gemini and Perplexity now decide which Web pages users see as sources, and a growing industry of generative

Google’s new EmbeddingGemma 2 can run on a phone. The model travels light. The vectors need their own suitcase. At 10 million documents, full-size float32 vectors alone take 30.7 GB of RAM. We got ear

EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimens

arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr

Editor’s note: This article is adapted from Thomas Kurian’s keynote address at Gemini at Work 2026. It includes a number of announcements: Gemini, a single, universal agent for work that answers your

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

Alteryx One Live Query and Google Cloud BigQuery redefine how enterprises handle complex, unstructured data at scale by reducing reliance on disconnected tools, minimizing data movement, and enabling

When we talk about agents, that doesn't necessarily mean we're talking about Python. In today's modern ecosystem, an agent might run as a high-concurrency Go microservice on Cloud Run, or live inside

arXiv:2610.15033v1 Announce Type: cross Abstract: Generative search engines such as ChatGPT, Gemini and Perplexity now decide which Web pages users see as sources, and a growing industry of generative

arXiv:2501.07972v2 Announce Type: replace-cross Abstract: The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Exist

Meta published a paper that might end the transformer era. For the last seven years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture. Transformer. But Transforme

arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for

Banger paper from Meta on AI research agents. (bookmark it) If you build AI-scientist systems, this one is worth your time. The result: A 27B open model beats the strongest open autoresearch baseline

arXiv:2610.12794v1 Announce Type: cross Abstract: Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization

arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the pra

arXiv:2610.16349v1 Announce Type: cross Abstract: Which context tokens drive a language model's answer? Graph-based tools such as attention rollout and attention flow answer this from a single forward

arXiv:2610.17079v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering (VQA) requires reasoning that extends beyond visible image content, demanding external commonsense and factual

arXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk

arXiv:2609.16517v1 Announce Type: cross Abstract: Resume screeners must infer job-relevant competence from resumes whose presentation can vary substantially in wording, structure, stylistic polish, an

arXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i

arXiv:2609.28290v1 Announce Type: new Abstract: Meaning identity (whether two sentences say the same thing after wording changes) is treated in retrieval and RAG as a geometric fact about independentl

arXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o

arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score, m

arXiv:2610.01861v1 Announce Type: new Abstract: Natural language descriptions can provide rich semantic representations of audio-visual urban scenes, yet datasets that jointly describe both auditory a

arXiv:2610.02713v1 Announce Type: new Abstract: Most KV-cache compression methods classify attention heads once, either offline or during prefill, and keep this classification fixed throughout generat

Automated lint: 17 errors, 59669 warnings, 3 info

arXiv:2609.35240v1 Announce Type: new Abstract: Artificial-intelligence studies using computed tomography (CT) for lung cancer are often broadly labelled 'prediction' despite addressing clinically dis

arXiv:2609.38021v1 Announce Type: cross Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cover

arXiv:2610.00253v1 Announce Type: cross Abstract: Audits of AI visibility summarise the brand recommendations of deployed language models into per-system profiles. We test whether such a profile descr

arXiv:2610.00087v1 Announce Type: cross Abstract: The advancement of natural language processing (NLP) has expanded AI-based text classification in the legal domain. However, accurately classifying le

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr

Agent-to-agent communication with a personal agent on top is wild. Wow. I underestimated how well models like Opus 5.5 can coordinate already. This opens a whole new set of experiences with agents. Bu

arXiv:2610.05690v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for literature search and synthesis. However, it is unclear whether they retrieve accurate bibliogr

arXiv:2610.09590v1 Announce Type: cross Abstract: Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefin

Live results, coding benchmarks included, agentic benchmarks included, domains and other classifications filters included. (Spoiler: DeepSeek-V4-Vision-Exp rules, but other models have their rule area

arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-

arXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti

arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ

arXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only th

Learn to build custom harnesses, folks! Here is an impressive paper showing the impact of a good custom harness on long-context work. GLM-5.3-Flash goes from 4.4% to 61.1% exact match on OfficeQA Pro

NVIDIA released VSS Blueprint 3.3, a framework that stitches together vision‑language models (Cosmos), LLMs (Nemotron) and retrieval‑augmented generation to convert live or recorded video into natural

I have been building a somewhat unusual local inference machine around two Huawei Atlas 300I Duo cards. They are relatively inexpensive, passive, dual-accelerator PCIe cards with 96 GB of device memor

arXiv:2610.02875v1 Announce Type: cross Abstract: Multilingual encoders can exhibit reduced retrieval effectiveness when queries and relevant documents differ in language, despite strong same-language

arXiv:2610.04912v1 Announce Type: cross Abstract: Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the comp

arXiv:2610.11049v1 Announce Type: new Abstract: We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from

arXiv:2610.11245v1 Announce Type: cross Abstract: KV-cache entries are stored before their future queries are known, but each decoding query needs precision in different places. We study this mismatch

Live results, coding benchmarks included, agentic benchmarks included, domains and other classifications filters included. (Spoiler: DeepSeek-V4-Vision-Exp rules, but other models have their rule area

arXiv:2610.15560v1 Announce Type: new Abstract: Existing navigation systems commonly rely on dedicated depth sensors or explicit depth reconstruction, while learning to generate trajectories directly