Knowledge catalogue
arXiv:2605.26646v1 Announce Type: new Abstract: LLM-based multi-agent systems decompose complex tasks into interacting roles, but most remain manually orchestrated by prompts, tools, and control rules
arXiv:2605.26457v1 Announce Type: cross Abstract: AI coding agents are increasingly used to write real-world software, but ensuring that their outputs are correct remains a fundamental challenge. Form
arXiv:2605.26380v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such
arXiv:2508.19988v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple r
arXiv:2605.25549v1 Announce Type: cross Abstract: High-quality expert chain-of-thought (CoT) data is one of the core bottlenecks in large language model (LLM) post-training. Existing data production m
arXiv:2605.23931v1 Announce Type: new Abstract: The formal verification of operating system kernels requires precise specifications that capture the intended behavior of system calls. Writing these sp
arXiv:2605.25891v1 Announce Type: cross Abstract: We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed
arXiv:2510.02361v2 Announce Type: replace-cross Abstract: Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to t
arXiv:2605.26036v1 Announce Type: new Abstract: Urban representation learning encodes complex urban environments into general-purpose embeddings for diverse downstream tasks and emerging urban foundat
arXiv:2605.25708v1 Announce Type: cross Abstract: Multi-domain task-incremental learning requires a model to sequentially acquire knowledge across visually diverse domains without forgetting prior tas
arXiv:2605.24267v1 Announce Type: new Abstract: Human conversation relies heavily on conversational implicature, in which speakers convey meanings that are suggested rather than explicitly stated. Alt
arXiv:2601.21726v2 Announce Type: replace Abstract: Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely
arXiv:2605.24879v1 Announce Type: new Abstract: Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for f
arXiv:2605.25052v1 Announce Type: new Abstract: Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these t
arXiv:2507.07644v4 Announce Type: replace Abstract: We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large language models (LLMs). FloorplanQA is grounded in struct
arXiv:2605.24432v1 Announce Type: new Abstract: Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns.
arXiv:2602.18527v2 Announce Type: replace-cross Abstract: Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. T
arXiv:2605.25036v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are
arXiv:2605.25676v1 Announce Type: new Abstract: We release Llamion, a family of 14B-parameter open-weight language models obtained by transforming Orion-14B into the standardized Llama-family architec
Mistral-7B v0.3 model achieves significant memory optimization when running at 128K context length in llama.cpp, reducing live VRAM usage from 22,657 MiB to 13,235 MiB while maintaining minimal perfor
arXiv:2505.23764v3 Announce Type: replace-cross Abstract: Spatial intelligence is essential for multimodal large language models (MLLMs) operating in the complex physical world. Existing benchmarks, h
arXiv:2605.25574v1 Announce Type: cross Abstract: Concept erasure has emerged as a key research direction for ensuring safe and ethical image synthesis in Text-to-Image (T2I) models. While existing st
arXiv:2605.24319v1 Announce Type: new Abstract: As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religiou
arXiv:2605.24261v1 Announce Type: new Abstract: A critical challenge facing clinicians managing chronic disease interventions is sustaining long-run patient health given limited information and resour
arXiv:2605.23912v1 Announce Type: cross Abstract: We present Raon-Speech, a top-performing 9B-parameter speech language model (SpeechLM) for English and Korean speech understanding, answering, and gen
arXiv:2605.24834v1 Announce Type: cross Abstract: Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversar
arXiv:2512.23995v2 Announce Type: replace-cross Abstract: Mixture-of-Experts architectures have become the standard for scaling large language models due to their superior parameter efficiency. To acc
arXiv:2605.24942v1 Announce Type: cross Abstract: Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation
arXiv:2605.24547v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards can improve LLM reasoning, but learning remains sample-inefficient when terminal rewards are sparse. This
arXiv:2605.24817v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have become an increasingly important paradigm for scaling Large Language Models (LLMs). As MoE models are incr
arXiv:2605.24117v1 Announce Type: new Abstract: Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience c
arXiv:2605.25534v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term th
arXiv:2605.25488v1 Announce Type: cross Abstract: Audio-driven talking-head generation has achieved remarkable progress with recent models such as AniTalker, FLOAT, and Sonic. Despite their success, m
arXiv:2605.25133v1 Announce Type: new Abstract: Reliably knowing when a language model is correct is almost as important as being correct. We introduce prover-verifier deliberation (PVD), an inference
arXiv:2509.25339v3 Announce Type: replace-cross Abstract: Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answerin
arXiv:2605.25981v1 Announce Type: new Abstract: We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-b
arXiv:2605.25256v1 Announce Type: new Abstract: Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We
arXiv:2605.24719v1 Announce Type: cross Abstract: Large Language Models (LLMs) have changed the possibilities of Interactive Storytelling systems that process free-text user input. However, as more of
arXiv:2605.23497v1 Announce Type: new Abstract: Large language models are increasingly used for legal research, yet their fixed training cutoffs and reliance on static parametric knowledge are at odds
arXiv:2605.22133v2 Announce Type: replace-cross Abstract: Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targe
arXiv:2603.06610v2 Announce Type: replace Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfor
arXiv:2605.23216v1 Announce Type: new Abstract: Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception t
arXiv:2605.23244v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approach
arXiv:2605.23572v1 Announce Type: cross Abstract: In the competitive landscape of sponsored search, balancing retrieval quality with production latency is a critical challenge. While large retrieval m
arXiv:2605.23628v1 Announce Type: new Abstract: Multi-task benchmarks have become a central pillar of machine learning research, yet their growing influence has incentivised benchmark gaming -- strate
arXiv:2605.23174v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of physiological signals from facial videos, offering strong potential for remote hea
arXiv:2605.23296v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate growing conversation histories that eventually exceed the model's context window. Context compaction via LLM-based su
arXiv:2605.23170v1 Announce Type: cross Abstract: Position-controlled evaluation is standard for retrieval tasks such as Needle-in-a-Haystack and RULER, but mainstream reasoning benchmarks do not cont
arXiv:2605.22903v1 Announce Type: cross Abstract: Benchmark accuracy is often implicitly assumed to reflect grounded visual understanding in vision-language models (VLMs), yet it remains unclear to wh
arXiv:2605.23904v1 Announce Type: new Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning
arXiv:2605.22841v1 Announce Type: cross Abstract: What happens when the strongest alliance member pressures a weaker member over territory and strategic control? We examine the Greenland sovereignty c
arXiv:2605.23171v1 Announce Type: cross Abstract: Recent advancements in instructional fine-tuning have injected noise into embeddings, with NEFTune (Jain et al., 2024) setting benchmarks using unifor
arXiv:2605.22907v1 Announce Type: new Abstract: Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal s
arXiv:2605.22111v1 Announce Type: new Abstract: Accurate modeling of aerodynamic loads is essential for understanding and predicting the responses of complex structural systems. However, these models
arXiv:2605.22243v1 Announce Type: new Abstract: Predictive modelling is important for health data analysis and data-driven clinical decision-making. However, predictive studies are challenging to desi
arXiv:2505.20349v2 Announce Type: replace-cross Abstract: Data-driven modeling of fluid dynamics has advanced rapidly with neural PDE solvers, yet a fair and strong benchmark remains fragmented due to
arXiv:2605.21834v1 Announce Type: new Abstract: Aligned models can misbehave in several ways: they are often sycophantic, fall victim to jailbreaks, or fail to include appropriate safety warnings. Con
arXiv:2605.21813v1 Announce Type: new Abstract: Discrete probability laws underpin statistical modeling, yet the catalog of interpretable distributions has expanded only gradually through centuries of
arXiv:2605.22368v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not j
arXiv:2605.22785v1 Announce Type: new Abstract: AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their p