Knowledge catalogue
arXiv:2605.21338v1 Announce Type: new Abstract: LLMs have demonstrated exceptional proficiency in a wide range of NLP tasks. However, a notable gap remains in practical data analysis scenarios, partic
arXiv:2605.21318v1 Announce Type: new Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimiza
arXiv:2605.20749v1 Announce Type: new Abstract: Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform thei
arXiv:2605.20745v1 Announce Type: cross Abstract: Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they
Many of the world’s fastest-growing AI startups are choosing to build their future — and the world’s — on Google Cloud because of our complete and open AI stack. We embed AI into every layer of our ar
arXiv:2605.20544v1 Announce Type: cross Abstract: Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations i
arXiv:2605.20994v1 Announce Type: new Abstract: Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a stand
arXiv:2605.21487v1 Announce Type: new Abstract: Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task t
arXiv:2605.20291v1 Announce Type: new Abstract: Large language models (LLMs) have enabled web agents that follow natural language goals through multi-step browser interactions. However, agents fine-tu
arXiv:2605.20795v1 Announce Type: new Abstract: Flow matching based video generative models have been increasingly relying on prepended Vision-Language Models (VLMs) to handle complex, instruction-bas
Francois Chollet observes that AI systems which always affirm user correctness without nuance or disagreement reduce his confidence in their reliability. This reflects a concern that uncritical agreem
arXiv:2605.21479v1 Announce Type: new Abstract: Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, man
arXiv:2605.20306v1 Announce Type: new Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous
arXiv:2605.20485v1 Announce Type: new Abstract: As autonomous agents increasingly execute end-to-end tasks under fixed monetary budgets, the pressing open question shifts from whether the budget is re
arXiv:2605.19988v1 Announce Type: cross Abstract: Documentation has long guided computer system tuning by distilling expert knowledge into per-parameter recommendations. Yet such guides capture only w
arXiv:2002.09053v3 Announce Type: replace Abstract: Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object det
arXiv:2605.19950v1 Announce Type: new Abstract: Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large languag
arXiv:2605.19337v1 Announce Type: new Abstract: A growing body of work explores how Large Language Models (LLMs) can be embedded in trading systems as agents that perceive market information, retrieve
This post likely discusses strategies and techniques for improving AI agent design and capabilities, possibly including methods for training agents to be more effective at complex tasks. The content a
arXiv:2605.20025v1 Announce Type: new Abstract: Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple per
arXiv:2605.20165v1 Announce Type: new Abstract: Vision-Language Models (VLMs) achieve strong performance on spatial question answering benchmarks, yet it remains unclear whether such gains reflect gen
CANTANTE addresses the challenge of optimizing LLM-based multi-agent systems where system-level performance scores are available but individual agent parameters cannot be directly optimized. The frame
arXiv:2605.19758v1 Announce Type: new Abstract: The ability to maintain and manipulate information over time is a fundamental aspect of living beings and Artificial Intelligence. While modern models h
arXiv:2605.18999v1 Announce Type: new Abstract: Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains se
arXiv:2602.23622v2 Announce Type: replace-cross Abstract: Significant progress has been made in the field of Instruction-based Image Editing Models (IIEMs). However, while these models demonstrate pla
arXiv:2605.18915v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-
arXiv:2510.12773v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) process every token through all layers of a transformer stack, causing wasted computation on simple queries and i
arXiv:2602.04279v2 Announce Type: replace Abstract: Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) rem
arXiv:2605.18918v1 Announce Type: cross Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web s
arXiv:2605.18872v1 Announce Type: cross Abstract: Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive r
arXiv:2603.11768v2 Announce Type: replace Abstract: Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong m
arXiv:2605.18795v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-o
arXiv:2603.17839v3 Announce Type: replace-cross Abstract: Verbal confidence -- prompting LLMs to state their confidence as a number or category -- is widely used to extract uncertainty estimates from
arXiv:2503.08633v2 Announce Type: replace Abstract: Machine unlearning is the task of updating a trained model to forget specific training data without retraining from scratch. In this paper, we inves
arXiv:2605.18853v1 Announce Type: cross Abstract: Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but
As models and harnesses improve, agents are taking on increasingly complex tasks that can run for hours or even days. But as we push agents to do more, this has surfaced a new operational problem: lon
arXiv:2605.19523v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire
arXiv:2508.16112v2 Announce Type: replace Abstract: Spectral analysis provides crucial clues for the elucidation of unknown materials. Among various techniques, infrared spectroscopy (IR) plays an imp
arXiv:2605.19645v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) have shown their remarkable capacities in many NLP tasks. However, their substantial size often pres
arXiv:2605.18895v1 Announce Type: cross Abstract: Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attribut
arXiv:2605.20170v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) have shown impressive performances in user-facing tasks such as question answering, as well as consistent improvemen
arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function o
arXiv:2605.19028v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method, yet its learned correction is static: the same low-rank update is ap
arXiv:2504.00470v2 Announce Type: replace-cross Abstract: To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of exis
LLMs are stateless (every time you reply to an LLM, you re-inject the entire conversation to a fresh inference) the purpose of memory is to provide continuity (in games we'd call it a 'persistent worl
arXiv:2605.18829v1 Announce Type: new Abstract: Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing m
arXiv:2605.19748v1 Announce Type: new Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation
arXiv:2510.18830v2 Announce Type: replace Abstract: The adoption of long context windows has become a standard feature in Large Language Models (LLMs), as extended contexts significantly enhance their
arXiv:2605.18817v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) generate text by iteratively denoising masked token sequences, offering a tradeoff between parallelism and quality comp
arXiv:2605.18884v1 Announce Type: cross Abstract: Multimodal emotion recognition aims to integrate text, audio, and video sources to understand human affective states. Although multimodal large langua
arXiv:2510.18924v3 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOT
arXiv:2605.18825v1 Announce Type: new Abstract: Prefix caching is a key optimization in Large Language Model (LLM) serving, reusing attention Key-Value (KV) states across requests with shared prompt p
arXiv:2605.19276v1 Announce Type: new Abstract: In recent years, the field of artificial intelligence has undergone a paradigm shift from task-specific small-scale models to general-purpose large lang
arXiv:2605.19932v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across in
arXiv:2605.20072v1 Announce Type: new Abstract: Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to ex
arXiv:2605.18805v1 Announce Type: cross Abstract: LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet ex
arXiv:2605.20110v1 Announce Type: new Abstract: Referring segmentation grounds natural-language queries to pixel-level masks, but extending it to complex scenarios with multiple instances, cross-categ
arXiv:2605.18791v1 Announce Type: cross Abstract: Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multi
arXiv:2603.05933v2 Announce Type: replace Abstract: Applying Small Language Models (SLMs) to Chinese character-driven generation remains challenging due to data scarcity and the difficulty of disentan
arXiv:2605.19738v1 Announce Type: cross Abstract: Graph Anomaly Detection (GAD) aims to identify atypical graph entities, such as nodes, edges, or substructures, that deviate significantly from the ma