Knowledge catalogue
arXiv:2605.16873v1 Announce Type: new Abstract: Diffusion priors have recently demonstrated strong capability in enhancing the quality of sparse-view 3D reconstruction by augmenting training views at
arXiv:2605.17300v1 Announce Type: new Abstract: We introduce HCLM, a hierarchical framework for general-purpose cooperative loco-manipulation with dual quadrupedal systems. Coordinating multi-robot co
arXiv:2605.17093v1 Announce Type: cross Abstract: Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference
arXiv:2605.16268v1 Announce Type: cross Abstract: Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it challenging to accurately direct customers to the a
arXiv:2603.20380v2 Announce Type: replace-cross Abstract: Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, but the applications through which
GoPerfect mission is to use an AI recruiting workforce that replaces the manual, low-leverage parts of recruiting. Instead, an agent decomposes recruiter intent and runs the work end to end to find to
arXiv:2605.17570v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large
arXiv:2605.17077v1 Announce Type: cross Abstract: Scaling robot policy learning is bottlenecked by the cost of collecting demonstrations, while language annotations for existing demonstrations are com
arXiv:2605.17106v1 Announce Type: new Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary st
A developer created a visualization tool that displays GPT-2's internal concept activations in real-time during text generation, representing the model's 'thinking' process as a 3D graph that updates
arXiv:2605.16457v1 Announce Type: cross Abstract: Transformer-based world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-ho
arXiv:2605.17930v1 Announce Type: new Abstract: While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of
arXiv:2605.16528v1 Announce Type: cross Abstract: The latest improvements in artificial intelligence (AI) raise new challenges for intellectual property laws, particularly concerning the inventorship
I've been thinking a lot about the two different groups of evals you need in general agents/agents which handle broad tasks: 1. Benchmark evals - this is a suite of up to 100 eval cases which test the
arXiv:2605.17902v1 Announce Type: new Abstract: Stochastic-process-based degradation modeling is a core approach for estimating the distribution of remaining useful life (RUL); however, the selection
arXiv:2601.20888v3 Announce Type: replace-cross Abstract: We study sampling from posterior distributions in Bayesian linear inverse problems where A, the parameters to observables operator, is computa
arXiv:2605.16632v1 Announce Type: cross Abstract: Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transf
arXiv:2605.17854v1 Announce Type: new Abstract: Conventional approaches to learning on graphs involve message passing along existing (i.e., positive) edges to update node features. However, these appr
arXiv:2605.16857v1 Announce Type: new Abstract: Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing
arXiv:2605.16615v1 Announce Type: new Abstract: In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For examp
arXiv:2605.12012v2 Announce Type: replace Abstract: Public-sector legal departments in the Netherlands face acute staff shortages, increased case volumes, and increased pressure to meet regulatory com
arXiv:2605.17333v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) typically samples multiple responses per prompt and assigns binary rewards based on individual cor
arXiv:2603.16947v2 Announce Type: replace-cross Abstract: Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging
arXiv:2605.18077v1 Announce Type: new Abstract: Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on i
arXiv:2503.02574v2 Announce Type: replace-cross Abstract: In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of n
arXiv:2605.17478v1 Announce Type: new Abstract: Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases
arXiv:2605.16301v1 Announce Type: cross Abstract: Single-turn benchmarks such as AnimalHarmBench (AHB) have established important baselines for measuring animal welfare alignment in large language mod
arXiv:2605.17640v1 Announce Type: cross Abstract: Retrieval-augmented generation from videos requires systems to retrieve relevant audiovisual evidence from large corpora and synthesize it into cohere
arXiv:2605.06017v2 Announce Type: replace Abstract: Sequence-level evaluations in autoregressive Large Language Models (LLMs) rely on highly dependent token generation. Establishing tight concentratio
arXiv:2601.08118v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as human simulators, both for evaluating conversational systems and for generating fine-tuning da
arXiv:2605.16865v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is widely used to inject new knowledge into language models, but it often degrades pretrained capabilities such as reasonin
arXiv:2605.17364v1 Announce Type: new Abstract: Media bias detection has predominantly been framed as a classification task: assign a political label to an article or outlet. We argue this framing is
arXiv:2605.18481v1 Announce Type: new Abstract: Interpreting the decisions of deep image classifiers remains challenging, particularly in black-box settings where model internals are inaccessible. We
arXiv:2605.17862v1 Announce Type: cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system
arXiv:2605.17360v1 Announce Type: new Abstract: Real-time duplex interaction is essential for multimodal AI systems operating in real-world scenarios, where models must continuously process streaming
arXiv:2605.17811v1 Announce Type: cross Abstract: Can a shared-weight recurrent Transformer develop distinct internal roles without being partitioned into separate modules? We study this in Asymmetric
arXiv:2605.06088v2 Announce Type: replace Abstract: Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semanti
arXiv:2605.16363v1 Announce Type: new Abstract: Smartphone scams are increasingly prevalent and typically manifest as multi-stage, cross-application processes with gradually emerging intent. Effective
arXiv:2605.16452v1 Announce Type: cross Abstract: Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiog
arXiv:2605.16858v1 Announce Type: cross Abstract: Autonomous Vehicles (AVs) must make reliable decisions in dense urban environments where pedestrian behavior is variable, sometimes abnormal, and ofte
arXiv:2605.18303v1 Announce Type: cross Abstract: World models built on recurrent state space architectures enable efficient latent imagination, yet remain physically unstructured, producing dynamics
arXiv:2605.16863v1 Announce Type: cross Abstract: Compositional diffusion models offer a promising route to long-horizon planning by denoising multiple overlapping sub-trajectories while ensuring that
arXiv:2605.17187v1 Announce Type: cross Abstract: Social media are shifting towards pluralism -- community-governed platforms where groups define their own norms. What violates rules in one community
arXiv:2605.17681v1 Announce Type: new Abstract: Humanoid and legged robots interact with the environment through intermittent contacts, making accurate motion estimation fundamentally dependent on rea
arXiv:2510.16609v3 Announce Type: replace-cross Abstract: Test-time augmentation, such as Retrieval-Augmented Generation (RAG) or tool use, critically depends on an interplay between a model's paramet
arXiv:2605.16346v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) have become a promising paradigm for solving complex tasks through role specialization, tool use, memory, and
arXiv:2605.17382v1 Announce Type: new Abstract: The rapid progress of generative artificial intelligence has exposed fundamental limitations in existing evaluation methodologies, particularly for open
arXiv:2605.18031v1 Announce Type: cross Abstract: We propose a quantum sidecar architecture family for future hybrid AI training and inference. The central idea is not to store an entire Transformer i
arXiv:2605.18407v1 Announce Type: cross Abstract: While modern Large Language Models (LLMs) and agentic artificial intelligence (AI) have demonstrated transformative capabilities in digital domains, t
arXiv:2605.18423v1 Announce Type: new Abstract: As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their
arXiv:2605.17169v1 Announce Type: new Abstract: Agentic AI is rapidly proliferating across diverse real-world domains such as software engineering, yet public trust has not kept pace. The central reas
arXiv:2605.17787v1 Announce Type: new Abstract: It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptive optimizers such as Adam in pre-training Large La
arXiv:2605.16651v1 Announce Type: new Abstract: Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model de
arXiv:2605.16843v1 Announce Type: new Abstract: India's Right to Information Act, 2005 gives every citizen the right to demand information from public authorities, yet in practice most people cannot m
arXiv:2605.16650v1 Announce Type: cross Abstract: Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously est
arXiv:2605.17789v1 Announce Type: cross Abstract: Memory systems for AI assistants were built for single-user dialogue and fail characteristically when applied to multi-party social group settings. Th
arXiv:2605.16470v1 Announce Type: cross Abstract: Adapting large language models (LLMs) to downstream tasks via full fine-tuning is increasingly impractical due to its computational and memory demands
arXiv:2605.18548v1 Announce Type: cross Abstract: Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalida
arXiv:2502.13957v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deplo
arXiv:2605.16671v1 Announce Type: new Abstract: Rapid biodiversity loss underscore the urgency of effective monitoring, yet manual surveys remain resource-intensive. While on-device AI offers a scalab