Knowledge catalogue
arXiv:2605.27315v1 Announce Type: new Abstract: Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language mod
arXiv:2605.27176v1 Announce Type: new Abstract: Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generat
The MiniMax M2 series was one of the most widely used open-weight LLM series earlier this year. Now, we got a technical report with some interesting tidbits. I summarized some of them below: 1. Full a
arXiv:2605.24765v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to cybersecurity question answering (QA) for critical tasks such as incident response and vulner
arXiv:2605.25685v1 Announce Type: new Abstract: Robust and accurate perception of humans in their 3D scene context is essential for integrating robots into everyday environments. Existing approaches,
arXiv:2605.24417v1 Announce Type: new Abstract: Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data
arXiv:2602.01086v2 Announce Type: replace Abstract: Background: As of 2026, Large Language Models (LLMs) demonstrate expert-level medical knowledge. However, deploying them as autonomous 'Clinical Age
arXiv:2605.23986v1 Announce Type: cross Abstract: Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and
arXiv:2605.24050v1 Announce Type: cross Abstract: Skill libraries allow LLM agents to load task-specific instructions on demand, letting non-expert users solve domain-specific tasks through natural la
arXiv:2605.25535v1 Announce Type: new Abstract: Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are wor
arXiv:2605.24411v1 Announce Type: new Abstract: Existing language model applications struggle to meet the demand for emotionally oriented support, primarily due to their inability to maintain deep, pe
arXiv:2605.23559v1 Announce Type: cross Abstract: Whole-slide image visual question answering (WSI-VQA) frames pathology as an extreme-context search problem: to answer a free-form clinical query, a s
arXiv:2605.22884v1 Announce Type: cross Abstract: Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so
arXiv:2605.22995v1 Announce Type: cross Abstract: Agentic AI systems are increasingly proposed for social-good domains, often invoking the United Nations Sustainable Development Goals (SDGs) as a voca
This post from Gary Marcus appears to reference a humorous or notable moment related to his work, with image attachments in Traditional Chinese that provide context to the claim that he 'has won again
arXiv:2605.22820v1 Announce Type: new Abstract: We propose the Integrable Context-Dependent Demand Network (ICDN), a demand-first neural model for multiproduct retail demand. The model learns log-dema
arXiv:2605.22003v1 Announce Type: new Abstract: Sentiment analysis, also referred to as opinion mining, primarily tries to extract opinion from any text-based data. In the context of movie reviews and
This guide demonstrates how to build a coding assistant using Weaviate's Model Context Protocol (MCP) integration, enabling retrieval-augmented generation (RAG) capabilities over codebases and documen
arXiv:2605.20284v1 Announce Type: new Abstract: Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, pa
arXiv:2605.21292v1 Announce Type: cross Abstract: Gradient-flow analyses show that simplified linear transformers can learn the in-context linear-regression algorithm, but they do not explain the fini
arXiv:2605.20459v1 Announce Type: new Abstract: In recent years, there has been a notable increase in the level of attention that is given to algorithms based on deep learning in the context of medica
Cybersecurity and password service provider 1Password LLC today expanded its collaboration with OpenAI Group PBC, releasing a Model Context Protocol server that lets the Codex coding agent pull creden
arXiv:2605.18760v1 Announce Type: cross Abstract: Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their health; but information in the record is complex,
arXiv:2605.19859v1 Announce Type: new Abstract: Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs
arXiv:2605.18842v1 Announce Type: new Abstract: Safe reinforcement learning in nonstationary environments requires safety mechanisms that adapt as environmental conditions change. Standard safe reinfo
arXiv:2605.16532v1 Announce Type: new Abstract: Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming:
arXiv:2605.17641v1 Announce Type: new Abstract: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using sema
arXiv:2605.16839v1 Announce Type: new Abstract: Chunked prefill has become a widely adopted serving strategy for long-context large language models, but efficient attention computation in this regime
arXiv:2605.16630v1 Announce Type: cross Abstract: Hybrid local--cloud agents enrich user requests with context from persistent working state before delegating capability-intensive subtasks to a cloud
arXiv:2605.18184v1 Announce Type: cross Abstract: Commonly available prior information, such as BIM models, floor plans, and remote sensing images, can provide valuable geometric and semantic context
arXiv:2605.18271v1 Announce Type: cross Abstract: With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and
arXiv:2605.17757v1 Announce Type: cross Abstract: INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations
arXiv:2605.16712v1 Announce Type: new Abstract: Long-context and memory systems usually treat personalization as a recall problem. In practice, many failures occur later, when a system commits: it tur
arXiv:2605.16883v1 Announce Type: new Abstract: Autonomous Graphical User Interface (GUI) agents often struggle with multi-step tasks due to constrained context windows and static policies that fail t
arXiv:2605.17170v1 Announce Type: new Abstract: Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context process
arXiv:2605.17613v1 Announce Type: cross Abstract: The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression
arXiv:2605.16481v1 Announce Type: cross Abstract: Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps
arXiv:2605.16972v1 Announce Type: cross Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive a
I cannot provide an accurate summary of this entry as the title appears to be truncated mid-sentence and lacks sufficient context. Based on the incomplete title, it likely discusses how software speci
arXiv:2605.15710v1 Announce Type: new Abstract: Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use ev
arXiv:2605.14487v1 Announce Type: cross Abstract: Autoregressive video diffusion models support real-time synthesis but suffer from error accumulation and context loss over long horizons. We discover
arXiv:2605.14002v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) embedded in agentic frameworks have transformed information retrieval from static, long context question answering into op
arXiv:2605.14889v1 Announce Type: cross Abstract: Online surgical phase recognition (SPR) underpins context-aware operating-room systems and requires committing to a prediction at every frame from pas
arXiv:2605.14604v1 Announce Type: new Abstract: This position paper argues that effective tutoring requires corrective friction: surfacing misconceptions and challenging them supportively to drive con
arXiv:2605.14115v1 Announce Type: new Abstract: Biomedical retrieval-augmented large language models (LLMs) often face evidence that is incomplete, misleading, or internally contradictory, yet evaluat
arXiv:2605.12697v1 Announce Type: cross Abstract: Length-dependent logit rescaling is widely used to stabilize long-context self-attention, but existing analyses and methods suggest conflicting invers
arXiv:2605.13723v1 Announce Type: cross Abstract: The phrase 'human in the loop' is increasingly used to imply a sense of safety in relation to AI decision systems. It shouldn't. There are contexts wh
arXiv:2605.13255v1 Announce Type: new Abstract: On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provid
arXiv:2605.12584v1 Announce Type: cross Abstract: Recently, multimodal graph learning (MGL) has garnered significant attention for integrating diverse modality information and structured context to su
arXiv:2605.12756v1 Announce Type: cross Abstract: Large language models (LLMs) are pretrained by minimizing the cross-entropy loss for next-token prediction. In this paper, we study whether this optim
arXiv:2605.11609v1 Announce Type: cross Abstract: On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedbac
arXiv:2605.11221v1 Announce Type: cross Abstract: Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck
💡 Why did @togethercompute choose NVIDIA Blackwell to serve DeepSeek-V4? Because NVIDIA Blackwell is built for the bottlenecks that matter most in long-context inference: → KV-cache pressure during de
arXiv:2605.09877v1 Announce Type: cross Abstract: We present Key-Value Means ('KVM'), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong
arXiv:2605.09725v1 Announce Type: new Abstract: On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for impro
arXiv:2605.08301v1 Announce Type: cross Abstract: Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fad
arXiv:2605.08317v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memor
arXiv:2512.24601v3 Announce Type: replace Abstract: We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive
arXiv:2605.10414v1 Announce Type: new Abstract: Rotary Positional Encoding (RoPE) is widely used in modern large language models. However, when sequences are extended beyond the range seen during trai