Knowledge catalogue
arXiv:2605.08158v1 Announce Type: cross Abstract: Long-video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, qua
arXiv:2602.01015v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly embedded in AI-based tutoring systems. Can they faithfully model novice reasoning and metacognitive ju
arXiv:2605.08678v1 Announce Type: new Abstract: Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonst
arXiv:2605.08954v1 Announce Type: cross Abstract: Molecular optimization in drug discovery aims to discover molecules with improved target properties, but practical lead optimization often requires mo
arXiv:2508.17497v2 Announce Type: replace-cross Abstract: Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by alignin
arXiv:2605.10391v1 Announce Type: cross Abstract: We introduce Phoenix-VL 1.5 Medium, a 123B-parameter natively multimodal and multilingual foundation model, adapted to regional languages and the Sing
The thing about 90% of TDMs [Technical Decision Makers] is that they're motivated primarily by NOT GETTING FIRED. These aren't people who browser Lobsters or push to GH on the weekend. These are peopl
arXiv:2605.09012v1 Announce Type: new Abstract: Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the
arXiv:2506.04289v3 Announce Type: replace Abstract: Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understo
arXiv:2605.08840v1 Announce Type: new Abstract: Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, es
arXiv:2605.09666v1 Announce Type: cross Abstract: Multiple Sclerosis (MS) is a chronic autoimmune disease that can significantly reduce the quality of life of a patient. Existing treatment options can
arXiv:2502.06818v3 Announce Type: replace Abstract: Recent works modify CLIP to perform open-vocabulary semantic segmentation in a training-free manner (TF-OVSS). In vanilla CLIP, patch-wise image rep
arXiv:2602.00327v2 Announce Type: replace Abstract: We explore the use of large language models (LLMs) for next-utterance anticipation in human dialogue. Despite recent advances in LLMs demonstrating
arXiv:2605.10674v1 Announce Type: cross Abstract: Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the
arXiv:2601.08321v3 Announce Type: replace Abstract: With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main
arXiv:2605.10889v1 Announce Type: cross Abstract: On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this sign
arXiv:2605.09692v1 Announce Type: new Abstract: Unpredictable behavior is often taken as evidence of control, yet stochastic dispersion and structured action control need not coincide. This paper test
arXiv:2605.08380v1 Announce Type: cross Abstract: AI agents are increasingly framed as software-engineering teammates, yet most research studies them inside human-centered workflows. Little is known a
arXiv:2605.07731v1 Announce Type: cross Abstract: This report benchmarks the performance of ENGINEERING Ingegneria Informatica S.p.A.'s EngGPT2MoE-16B-A3B LLM, a 16B parameter Mixture of Experts (MoE)
arXiv:2605.07846v1 Announce Type: new Abstract: Coarse-mask local image editing asks a model to modify a user-indicated region while preserving the surrounding scene. In practice, however, rough masks
arXiv:2605.06941v1 Announce Type: new Abstract: We introduce a causal aware foundation-model framework for real time optimal decision making in discrete choice environments. We propose a constrained t
arXiv:2605.07325v1 Announce Type: cross Abstract: Deploying massive large language models (LLMs) as continuous cognitive engines for robotics is bottlenecked by the time-to-first-token (TTFT) latency
arXiv:2605.06911v1 Announce Type: new Abstract: Subseasonal-to-seasonal (S2S) temperature forecasts, spanning several weeks to a few months, are critically needed in agriculture practice, energy plann
arXiv:2605.07455v1 Announce Type: new Abstract: Visual-prompt-guided edit transfer aims to learn image transformations directly from example pairs, offering more precise and controllable editing than
arXiv:2605.07389v1 Announce Type: cross Abstract: The integration of machine learning (ML) into complex software systems has increased challenges in collaboration and communication (CoCo) of the teams
arXiv:2510.02371v2 Announce Type: replace-cross Abstract: Smart grids are exposed to passive eavesdropping, where attackers listen silently to communication links. Although no data is actively altered
arXiv:2605.07817v1 Announce Type: cross Abstract: Human visual reasoning is governed by active vision, a process where metacognitive control drives top-down goal-directed attention, dynamically routin
arXiv:2605.06978v1 Announce Type: cross Abstract: Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable contex
arXiv:2605.05340v2 Announce Type: replace-cross Abstract: As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awa
arXiv:2605.07622v1 Announce Type: new Abstract: Gender bias in large language models has primarily been investigated for English, while languages with grammatical or morphological gender remain compar
arXiv:2605.07877v1 Announce Type: new Abstract: Robot swarms promise scalable assistance in complex and hazardous environments. Task planning lies at the core of human-swarm collaboration, translating
arXiv:2605.06728v1 Announce Type: cross Abstract: Interpreting transcriptomic data is one of the most common analytical tasks in modern biology. Yet most current models either consume expression profi
arXiv:2605.05806v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decode
arXiv:2605.07977v1 Announce Type: new Abstract: Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improv
arXiv:2605.07799v1 Announce Type: cross Abstract: Training foundation models is computationally intensive and often slow to converge.We introduce PIQL,Privileged Information for Quick and Quality Lear
With AI coding tools like Antigravity and Claude Code, I can build a working web app in record time. But deploying it? That's where I'd historically lose the rest of the afternoon to Dockerfiles, IAM
arXiv:2605.04098v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated promise on publicly available dermatology benchmarks. However, benchmark performance may not
arXiv:2605.04576v1 Announce Type: new Abstract: This paper presents the first benchmark for the task of automatic part-of-speech (POS) tagging for the Tajik language. Despite the existence of multilin
arXiv:2511.20284v2 Announce Type: replace-cross Abstract: Precise access control decisions are crucial for the security of both traditional applications and emerging agent-based systems. Typically, th
arXiv:2605.04413v1 Announce Type: new Abstract: Structural causal models provide a unified semantics for interventions and counterfactuals, but most identifiability results rely on restrictive assumpt
arXiv:2605.05204v1 Announce Type: new Abstract: The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterpa
arXiv:2605.04651v1 Announce Type: cross Abstract: Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memor
arXiv:2605.03952v1 Announce Type: cross Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The chal
arXiv:2605.05040v1 Announce Type: new Abstract: On-policy distillation is an efficient alternative to reinforcement learning, offering dense token-level training signals. However, its reliance on a st
arXiv:2605.04075v1 Announce Type: cross Abstract: Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the vis
arXiv:2601.00264v2 Announce Type: replace Abstract: Multimodal learning has revolutionized general domain tasks, yet its application in scientific discovery is hindered by the profound semantic gap be
arXiv:2605.04970v1 Announce Type: new Abstract: Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly. However, extending model capabilities to
arXiv:2605.03195v1 Announce Type: new Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibiliti
arXiv:2605.03213v1 Announce Type: cross Abstract: Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocol
arXiv:2605.00846v1 Announce Type: new Abstract: Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at
At Google, we see firsthand how cyber threats can outpace traditional defense mechanisms — and how agentic threat intelligence can help bridge the gap. We have a vision for agentic defense where auton
arXiv:2605.02832v1 Announce Type: new Abstract: Deciding how to distribute work between humans and AI systems is a central challenge in organisational design. Most approaches treat this as a binary ch
arXiv:2605.03863v1 Announce Type: cross Abstract: The visual environment is a fundamental yet unquantified determinant of mental health. While the concept of the environmental exposome is well establi
arXiv:2603.18196v3 Announce Type: replace-cross Abstract: Investigating cybersecurity incidents requires collecting and analyzing evidence from multiple log sources, including intrusion detection aler
arXiv:2605.01750v1 Announce Type: cross Abstract: Grounding is the collaborative process of establishing mutual belief sufficient for the current communicative purpose. While static grounding maps lan
arXiv:2605.02244v1 Announce Type: cross Abstract: Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-ho
arXiv:2605.02106v1 Announce Type: new Abstract: Contemporary artificial intelligence systems achieve strong performance through large-scale parameterization, retrieval augmentation, and training on ex
arXiv:2605.03953v1 Announce Type: cross Abstract: Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low
arXiv:2605.03792v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into legal workflows. However, existing benchmarks primarily address proxy tasks, such as bar e
arXiv:2605.01392v1 Announce Type: cross Abstract: Recent advancements in Large Language Models (LLMs) have demonstrated significant potential across a wide range of software engineering tasks, includi