Knowledge catalogue
arXiv:2606.07521v1 Announce Type: cross Abstract: This study investigates the phenomenon of hallucinations in domain-adapted Large Language Models (LLMs), focusing on the fine-tuning of the Llama-2 mo
arXiv:2605.05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
arXiv:2606.08850v1 Announce Type: cross Abstract: Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output select
arXiv:2606.07547v1 Announce Type: cross Abstract: Speech-based large language models are typically constrained to spoken replies, which limits their user-facing outputs to what can be verbalized and s
arXiv:2606.07712v1 Announce Type: cross Abstract: Progress in AI-driven crystal materials science has so far been carried by narrow architectures purpose-built for individual tasks -- graph neural net
arXiv:2511.18676v2 Announce Type: replace-cross Abstract: Current vision-language models (VLMs) in medicine are primarily designed for categorical question answering (e.g., 'Is this normal or abnormal
arXiv:2606.09457v1 Announce Type: new Abstract: Embodied policies typically map current observations directly to actions, leaving candidate-action consequences implicit. World models provide predictiv
arXiv:2606.07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patc
arXiv:2602.15327v2 Announce Type: replace-cross Abstract: Machine learning model performance improvements tend to arise from competition and application. For deployment, we consider prescriptive scali
As generative AI moves from experimental pilots to massive production environments, the efficiency of your infrastructure becomes the ultimate differentiator. One way to get the most out of it and min
arXiv:2509.16136v5 Announce Type: replace Abstract: Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iter
arXiv:2606.09399v1 Announce Type: new Abstract: We present SUPERBROWSER, an autonomous web-navigation agent designed against a single guiding hypothesis: a web agent should browse the way a person bro
arXiv:2606.07812v1 Announce Type: new Abstract: Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect that richness. Yet the LLMs used by all are built by t
arXiv:2606.08034v1 Announce Type: cross Abstract: Symbolic benchmarks have emerged as a key approach to assess model robustness under minor modifications to STEM-related questions. However, existing s
arXiv:2511.05017v2 Announce Type: replace Abstract: Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual informati
arXiv:2606.08032v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and di
arXiv:2509.09151v2 Announce Type: replace-cross Abstract: Research in video understanding has advanced rapidly, driven by increasingly diverse datasets and more powerful model architectures. While exi
arXiv:2606.08098v1 Announce Type: new Abstract: Majority voting over sampled answers is the dominant unsupervised aggregator for multi-sample LLM inference. We show that piping the signals every sampl
arXiv:2603.06915v2 Announce Type: replace Abstract: The extraction of structured information from raw text is a fundamental component of many NLP applications, including document retrieval, ranking, a
arXiv:2606.07402v1 Announce Type: new Abstract: Language agents are increasingly deployed over accumulating multimodal information, yet existing benchmarks assume a human-human form with sparse visual
arXiv:2606.06823v1 Announce Type: cross Abstract: While deep learning has excelled in various domains, its application to sequential decision-making in finance remains challenging due to the low Signa
arXiv:2603.07704v2 Announce Type: replace Abstract: Inter-object relations underpin spatial intelligence, yet existing representations -- linguistic prepositions or object-level scene graphs -- are to
arXiv:2502.00225v4 Announce Type: replace-cross Abstract: We evaluate the ability of the current generation of large language models (LLMs) to help a decision-making agent facing an exploration-exploi
arXiv:2606.06574v1 Announce Type: new Abstract: Large language models (LLMs) perform inference by following a fixed depth and order, non-recurrent execution of all layers. We reveal the wide existence
arXiv:2606.05658v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge, but conventional pipeli
arXiv:2606.06462v1 Announce Type: new Abstract: Benchmarks are fundamental for evaluating and advancing LLMs and MLLMs by providing standardized and explicit measures of performance. However, their co
arXiv:2606.05682v1 Announce Type: new Abstract: Demand for low-precision inference, including NVFP4-based approaches, has grown as large language models are increasingly deployed in latency and cost c
arXiv:2606.05950v1 Announce Type: new Abstract: Text-guided image editing has advanced rapidly with diffusion models and unified multimodal foundation models. However, most existing methods remain con
arXiv:2605.04733v2 Announce Type: replace Abstract: Text-based role-playing models can imitate character styles, but often fail to capture scene atmosphere and evolving tension, which are crucial for
arXiv:2606.05608v1 Announce Type: cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into s
arXiv:2602.09574v2 Announce Type: replace Abstract: Tree-search decoding is an effective form of test-time scaling for large language models (LLMs), but real-world deployment often imposes a fixed per
arXiv:2606.06025v1 Announce Type: new Abstract: Scientific peer review generation has attracted increasing attention for reducing reviewing burdens and providing timely feedback. However, existing Lar
arXiv:2510.17256v2 Announce Type: replace Abstract: Large language models have exhibited impressive performance across a broad range of downstream tasks in natural language processing. However, how a
arXiv:2606.05677v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon ta
arXiv:2606.05177v1 Announce Type: new Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and
Token costs are why there will be no saas apocalypse / good dev tools are cached intelligence for agents! The popular theory goes: agents can write code, so they'll just rebuild every tool from scratc
arXiv:2606.06369v1 Announce Type: new Abstract: Learning-driven Scene Graph Generation (SGG) models excel on frequent relation types but degrade sharply under annotation sparsity, failing to capture r
We've made a breakthrough in self-evolving AI scientists moving from 'search' to 'principled discovery': Scientific discovery requires that the search space itself changes, and an AI scientist must pe
arXiv:2606.06113v1 Announce Type: new Abstract: Despite generating increasingly photorealistic images, text-to-image (T2I) models still exhibit localized, subtle, and structurally complex failures. Di
arXiv:2606.04111v1 Announce Type: cross Abstract: Indoor UAV navigation requires efficient exploration, scene understanding, and reliable trajectory execution under limited field-of-view observations.
arXiv:2606.04752v1 Announce Type: cross Abstract: Transformers consuming multi-channel scalar signals must embed C simultaneous values into one d_{ext{model}}-dimensional vector per time step. We empi
arXiv:2606.04262v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for everyday health questions, including whether a user can safely take another dose of an over-the
arXiv:2507.21892v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucination in LLMs by incorporating external knowledge, but relies on chunk-based retrieval that l
arXiv:2604.04944v2 Announce Type: replace-cross Abstract: Multiple-choice questions (MCQs) are widely used to evaluate large language models (LLMs). However, LLMs remain vulnerable to the presence of
arXiv:2603.10044v2 Announce Type: replace-cross Abstract: A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never
arXiv:2606.04592v1 Announce Type: cross Abstract: LLM-based digital twins promise to scale and accelerate market research, but most published twins are either coarse persona bots conditioned on a few
arXiv:2606.04264v1 Announce Type: new Abstract: Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single archi
arXiv:2606.04632v1 Announce Type: cross Abstract: Mechanical ventilation for Acute Respiratory Distress Syndrome (ARDS) requires balancing competing physiological goals, including oxygenation, lung pr
arXiv:2606.03280v1 Announce Type: new Abstract: Recent work shows that language models can transmit behavioural traits through hidden signals in generated data during training. We ask whether a more d
arXiv:2606.03811v1 Announce Type: cross Abstract: A computer worm is malware that spreads on a network by replicating itself from one machine to another. Traditional worms, like WannaCry, exploited pr
arXiv:2606.03089v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to prov
arXiv:2604.17220v2 Announce Type: replace-cross Abstract: Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations managemen
arXiv:2606.02859v1 Announce Type: cross Abstract: How can a population of agents self-orchestrate and self-adapt into stronger collective intelligence without centralized control? Inspired by Friedric
arXiv:2606.03094v1 Announce Type: new Abstract: Recent advances in language models have established reinforcement learning as the primary paradigm for eliciting self-correction and long-chain reasonin
arXiv:2606.03761v1 Announce Type: new Abstract: Frame analysis of migration news is a socially consequential task: media scholars and researchers who study how migration is narrated need tools that ar
arXiv:2602.10352v2 Announce Type: replace-cross Abstract: Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitiv
arXiv:2606.03243v1 Announce Type: new Abstract: Modern text-to-image models have achieved strong visual synthesis, yet remain unreliable when prompts require implicit visual constraints, relational re
arXiv:2606.03968v1 Announce Type: cross Abstract: Rubric-based RL is a promising route for extending reinforcement learning beyond verifiable rewards, yet existing methods optimize rubrics while treat
arXiv:2606.03057v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for molecular tasks, but it remains unclear which molecular representation to use. We present a sys