Knowledge catalogue
arXiv:2605.29800v1 Announce Type: new Abstract: LLM-as-a-judge panels aggregate votes from multiple models, with the expectation that diverse models yield more reliable evaluations. We develop a frame
arXiv:2605.29495v1 Announce Type: new Abstract: Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers
arXiv:2605.29829v1 Announce Type: new Abstract: Leveraging Large Language Models (LLMs) to automatically formulate and solve optimization problems from natural language has emerged as an efficient par
arXiv:2605.29711v1 Announce Type: cross Abstract: User satisfaction with AI assistants is highly personalized: the same response may satisfy one user but disappoint another depending on what each user
arXiv:2605.29815v1 Announce Type: new Abstract: The growing number of submitted papers has motivated the exploration of Large Language Models (LLMs) as a means to support and augment the peer review p
arXiv:2605.30284v1 Announce Type: new Abstract: Scientific discovery is an inherently creative and uncertain process, requiring reasoning beyond the recall of known knowledge. While many benchmarks ha
arXiv:2605.29579v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have achieved rapid progress in vision-language understanding, they remain prone to multimodal hallucinat
arXiv:2605.29224v1 Announce Type: cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating
arXiv:2603.02803v2 Announce Type: replace Abstract: Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex
arXiv:2602.15382v2 Announce Type: replace Abstract: Multi-Agent Systems (MAS) powered by Large Language Models have unlocked advanced collaborative reasoning, yet they remain bottlenecked by discrete
arXiv:2605.30189v1 Announce Type: cross Abstract: We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while pre
arXiv:2605.29230v1 Announce Type: cross Abstract: Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises serious ethical, legal, and
arXiv:2605.29601v1 Announce Type: cross Abstract: As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a centra
arXiv:2602.16610v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise
arXiv:2605.27785v1 Announce Type: new Abstract: The fastest-growing data in production today is unstructured text: agent traces, chat logs, reasoning chains, model outputs. People want to analyze it,
arXiv:2605.27995v1 Announce Type: new Abstract: Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations oft
arXiv:2605.27485v1 Announce Type: cross Abstract: Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used i
arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while preserving its deploym
arXiv:2605.27737v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly attractive for multimodal quality assessment, but their default reliance on autoregressive text generatio
arXiv:2605.28010v1 Announce Type: new Abstract: Self-evolving large language models (LLMs) learn by generating their own training tasks and solutions, reducing reliance on human-curated supervision. H
arXiv:2605.28139v1 Announce Type: new Abstract: Building competitive automatic speech recognition (ASR) models usually requires large-scale au- dio supervision, which makes reproduction and specializa
arXiv:2503.02857v5 Announce Type: replace-cross Abstract: In the age of increasingly realistic generative AI, robust deepfake detection is essential for mitigating fraud and disinformation. While many
arXiv:2605.28163v1 Announce Type: cross Abstract: Multilingual Large Language Models (mLLMs) leaderboards report per-language accuracy but rarely explain why disparities emerge, leaving systemic biase
arXiv:2605.28515v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become an integral part of software development, especially with the advent of agentic capabilities. Yet, many front
arXiv:2605.27390v1 Announce Type: cross Abstract: Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck
arXiv:2605.28389v1 Announce Type: new Abstract: While large language models have made significant progress in mathematical reasoning, they remain unreliable at judging the correctness of their own sol
arXiv:2605.28188v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factuall
arXiv:2605.28500v1 Announce Type: cross Abstract: Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantific
arXiv:2605.28013v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision.
arXiv:2605.28617v1 Announce Type: new Abstract: LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime o
arXiv:2605.27734v1 Announce Type: new Abstract: Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude lar
Release: llm-anthropic 0.25.1 New model: Claude Opus 4.8 (claude-opus-4.8). New -o fast 1 option for fast mode, for organizations with that feature enabled on their account. Default max_tokens for eac
arXiv:2605.28231v1 Announce Type: cross Abstract: We present ProgVLA, a compact vision-language-action (VLA) model designed for reliable robot manipulation under tight compute and memory budgets. The
arXiv:2605.28122v1 Announce Type: cross Abstract: A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while th
arXiv:2605.28179v1 Announce Type: new Abstract: Scaling laws guide large language model training by relating compute to cross-entropy loss, and recent work further extends them to predict downstream b
arXiv:2605.27886v1 Announce Type: new Abstract: Tactile sensing is essential for robots to achieve human-like gentle manipulation. However, existing Vision-Language-Action (VLA) models struggle to exp
arXiv:2602.14862v2 Announce Type: replace-cross Abstract: Temperature scaling is a simple method that allows to control the uncertainty of probabilistic models. It is mostly used in two contexts: impr
arXiv:2605.27767v1 Announce Type: cross Abstract: Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at
arXiv:2605.27673v1 Announce Type: new Abstract: Complex-valued Neural Networks (CVNNs) are often motivated by domains where information is naturally encoded in magnitude and phase. Yet complex-valued
arXiv:2605.28069v1 Announce Type: new Abstract: Adaptive context compression is vital for scaling Large Language Models (LLMs) to complex, multi-turn agent tasks. However, rule-based compression metho
arXiv:2605.26533v1 Announce Type: cross Abstract: Automated industrial inspection requires both precise defect localization and structured maintenance report generation; in current practice these task
arXiv:2605.26174v1 Announce Type: cross Abstract: Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated
arXiv:2605.26772v1 Announce Type: new Abstract: Large reasoning models (LRMs) generate chain-of-thought (CoT) traces before producing final outputs, introducing a dynamic internal state that may compl
arXiv:2505.13775v4 Announce Type: replace-cross Abstract: Recent impressive results from large reasoning models have been interpreted as a triumph of Chain of Thought (CoT), and especially of the proc
arXiv:2605.26994v1 Announce Type: new Abstract: Charts are widely used to present complex data for analysis and decision making. Existing chart understanding benchmarks mainly focus on static charts,
arXiv:2605.27051v1 Announce Type: cross Abstract: Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up
arXiv:2603.16870v2 Announce Type: replace-cross Abstract: Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabil
arXiv:2601.09001v4 Announce Type: replace Abstract: Deploying LLMs raises two coupled challenges: (1) monitoring--estimating where a model underperforms as traffic and domains drift--and (2) improveme
arXiv:2411.02355v4 Announce Type: replace-cross Abstract: Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across differen
arXiv:2602.02518v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly rely on external knowledge to improve factuality, yet many real-world knowledge sources are organize
arXiv:2605.26394v1 Announce Type: new Abstract: Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench,
arXiv:2605.26761v1 Announce Type: new Abstract: Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data
arXiv:2605.27015v1 Announce Type: new Abstract: Despite impressive multilingual capabilities, large language models (LLMs) remain poorly evaluated on literary knowledge in non-English languages. We in
arXiv:2605.27210v1 Announce Type: cross Abstract: We adapt Microsoft's QuantumKatas -- a well-established quantum computing curriculum -- from Q# to Qiskit, the most widely-adopted quantum computing f
arXiv:2605.27081v1 Announce Type: cross Abstract: Fine-grained Mixture-of-Experts (MoE) models sparsely activate only a subset of experts per token, reducing activated computation while maintaining hi
arXiv:2601.10566v5 Announce Type: replace Abstract: Entity-level unlearning is usually evaluated by what a model says: whether it stops naming the target, refuses a query, or shifts a Truth Ratio dist
arXiv:2605.26735v1 Announce Type: new Abstract: Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior wor
arXiv:2605.27294v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems can respond incorrectly even when the correct passage was retrieved. The model must still read the retrieve
arXiv:2510.09606v2 Announce Type: replace Abstract: With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still strug
arXiv:2511.04711v2 Announce Type: replace-cross Abstract: Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, a