Search: “context”

arXiv:2608.07267v1 Announce Type: new Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models (VLMs) into vision-language-action (VLA) policies t

After seeing the benchmark results for the full release of DS v4 Flash 0731, I replaced my 2 x 16GB DDR4 ram sticks with 2 x 32GB DDR4 ram sticks to get a max supported of 128 GB RAM, in hope to be ab

I’m running DSV4F 0731 on dual spark, and honestly… wow. It’s an absolute workhorse, and the benchmarks are real. Everyday tasks with Hermes agent? Effortless. Coding tasks with OpenCode? I’m genuinel

Disclaimer - no LLM was used to write this post/note As larger post about my setup will come later, want to give heads-up to folks who use VLLM and >= 2 GPUs. So I have pretty meaty server (8 channel

arXiv:2608.05592v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved strong progress in video understanding, yet it remains challenging because the token limitation m

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive L

arXiv:2608.05367v1 Announce Type: new Abstract: Counterfactual analysis aims to predict potential outcomes under hypothetical scenarios, offering valuable insights for decision-making. This paper inve

arXiv:2608.06227v1 Announce Type: cross Abstract: Despite advances in artificial intelligence (AI) across multiple sectors, today's AI tools, including deep learning and generative AI, still fail when

At Google Cloud, securing your data and business systems is our foundational commitment. We empower our customers with the tools, governance, and infrastructure needed to securely deploy workloads and

arXiv:2608.06088v1 Announce Type: new Abstract: Robotics simulators serve as a foundational infrastructure for embodied AI, facilitating safe and scalable robotic system development. NVIDIA Isaac Sim

arXiv:2608.05872v1 Announce Type: cross Abstract: Standard Large Language Models (LLMs) execute layers sequentially. Dynamic layer routing, i.e. search for a different execution path through layers in

arXiv:2608.06292v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves question answering by grounding large language models (LLMs) in external knowledge such as text corpora. H

arXiv:2608.06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formula

arXiv:2608.05876v1 Announce Type: new Abstract: User requests serve as research specifications for deep research agents, shaping what evidence to seek and how to synthesize it. In personalized deep re

arXiv:2608.05774v1 Announce Type: new Abstract: Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primari

arXiv:2608.05810v1 Announce Type: new Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: p

arXiv:2608.05423v1 Announce Type: cross Abstract: In generative training, a model produces an output and is penalised for its difference from an example. With one output per comparison, a model that p

arXiv:2608.05369v1 Announce Type: cross Abstract: Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in r

Following up on yesterday's post about running everyone's faves on 2 x 16gb cards while maximizing performance and KV. Previous post data used abandoned Cu130 VLLM image. Stats here are done on cu129-

arXiv:2512.20661v2 Announce Type: replace Abstract: Transformer-based pre-trained language models (PLMs) excel in text classification but suffer from attention dilution and attention sink effects, for

arXiv:2608.04576v1 Announce Type: new Abstract: Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb stud

arXiv:2608.05004v1 Announce Type: new Abstract: Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including 'delusi

arXiv:2608.04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing sy

The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling their use across diverse hardware and software plat

arXiv:2608.04365v1 Announce Type: new Abstract: Audits have emerged as a critical instrument for algorithmic governance, providing a mechanism for external scrutiny and governance of machine learning

arXiv:2511.11413v2 Announce Type: replace Abstract: Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the actual stochastic weights, bas

arXiv:2608.05013v1 Announce Type: cross Abstract: LLM agents are increasingly applied to open-ended everyday requests that span work, study, and life. These tasks are long-horizon, cross-environment,

arXiv:2608.04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so th

arXiv:2608.04011v1 Announce Type: cross Abstract: This article examines the enduring epistemic and methodological crisis of traditional legal practice in light of the opportunities and constraints int

arXiv:2608.04562v1 Announce Type: new Abstract: Agent skills are increasingly optimized by automated feedback loops, producing long structured artifacts whose internal value remains unclear. We study

Most agent memory setups run a model call on the way in. Something reads the turn, decides whether it's worth keeping, rewrites it into a 'memory', tags it with a type and an importance score. That's

arXiv:2601.19138v2 Announce Type: replace-cross Abstract: Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security asse

arXiv:2608.03711v1 Announce Type: cross Abstract: In human visual perception, uppercase lettering serves as a natural salience cue that captures attention within lowercase text. In this paper, we pres

arXiv:2608.03674v1 Announce Type: new Abstract: Causal diagnostic models must explain how conclusions follow from evidence because diagnoses guide repairs and treatments. Yet serious cases are scarce,

arXiv:2608.03796v1 Announce Type: cross Abstract: Small language models are often the only option for deployment under tight latency, cost, and on-premises constraints, but they are rarely trained fro

arXiv:2608.03028v1 Announce Type: new Abstract: Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision. Existing medical evaluations

arXiv:2608.02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks. However, reliable tool-use planning remains

arXiv:2203.17257v2 Announce Type: replace Abstract: Salient Object Ranking (SOR) aims to estimate the relative saliency order among multiple salient objects. While SOR has been extensively studied in

arXiv:2604.01973v2 Announce Type: replace Abstract: When evaluating identity-focused tasks such as personalized generation and image editing, existing vision encoders entangle object identity with bac

arXiv:2608.02993v1 Announce Type: new Abstract: (Flat) Reinforcement Learning (RL) agents face significant challenges in environments with sparse rewards that require long-horizon reasoning. A compell

Prime Agent is an open-source coding and research agent for general and long-running work. A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficien

arXiv:2608.02751v1 Announce Type: cross Abstract: Existing deep-research agents use a search-visit workflow that retrieves and reads whole pages, without considering the addressable structure that web

arXiv:2511.21214v4 Announce Type: replace-cross Abstract: Explicit safety policies can improve reasoning-model safety, but their effective coverage may lag behind evolving jailbreak strategies. We stu

arXiv:2608.03952v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide conversational practice for English-as-a-second-language (ESL) learners. Effective ESL tut

arXiv:2608.04007v1 Announce Type: cross Abstract: Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning meth

arXiv:2608.00622v1 Announce Type: new Abstract: Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing m