Knowledge catalogue
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:2605.10187v1 Announce Type: new Abstract: Scientific reasoning is a key aspect of human intelligence, requiring the integration of multimodal inputs, domain expertise, and multi-step inference a
arXiv:2605.09266v1 Announce Type: new Abstract: We introduce SeePhys Pro, a fine-grained modality transfer benchmark that studies whether models preserve the same reasoning capability when critical in
arXiv:2605.10376v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have advanced rapidly in multimodal perception and language understanding, yet it remains unclear whether they can reliabl
arXiv:2605.10453v1 Announce Type: cross Abstract: Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model
arXiv:2604.02608v2 Announce Type: replace Abstract: Activation steering presupposes that task-relevant behaviors correspond to linear directions in activation space -- directions that should both stee
arXiv:2605.08366v1 Announce Type: new Abstract: We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test W
arXiv:2605.09536v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism tra
arXiv:2605.10388v1 Announce Type: new Abstract: End to end (E2E) autonomous driving trajectory prediction is often trained with camera frames sampled at the highest available temporal frequency, assum
arXiv:2502.01237v3 Announce Type: replace Abstract: Direct Alignment Algorithms (DAAs) simplify LLM alignment by directly optimizing policies, bypassing reward modeling and RL. While DAAs differ in th
arXiv:2605.10211v1 Announce Type: cross Abstract: Government transparency laws, like the Freedom of Information (FOIA) acts in the United States and United Kingdom, and the Woo (Open Government Act) i
arXiv:2605.08541v1 Announce Type: new Abstract: Neural scaling laws approximate a language model's loss as a power-law function of parameter count N and token count D. Following Chinchilla-style compu
arXiv:2602.17283v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on f
arXiv:2605.09227v1 Announce Type: new Abstract: [Abridged] Using a Large Language Model (LLM) as an automatic rater (LLM-as-a-judge) is cheap but potentially biased: some judges run lenient, others st
arXiv:2605.09862v1 Announce Type: cross Abstract: Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve
arXiv:2605.08288v1 Announce Type: cross Abstract: Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated
arXiv:2605.10716v1 Announce Type: new Abstract: Large language models are increasingly deployed with test-time strategies: sample N responses, score them with a reward model or verifier, and return th
arXiv:2605.08318v1 Announce Type: cross Abstract: We study the problem of architecture selection for deep learning models trained to solve partial differential equations (PDEs), asking when transforme
When is the last time a general purpose LLM (putting aside hybrid systems like Claude Code with special purpose symbolic harnesses) last completely blew away all competing prior models? GPT-4 relative
arXiv:2605.10434v1 Announce Type: new Abstract: Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving i
arXiv:2605.06819v1 Announce Type: new Abstract: Autoregressive generation lies at the heart of the mechanism of large language models. It can be viewed as the repeated application of a next-token gene
arXiv:2605.07324v1 Announce Type: cross Abstract: Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior w
arXiv:2605.06869v1 Announce Type: new Abstract: AI agent research spans a wide spectrum: from RL agents that learn from scratch to foundation model agents that leverage pre-trained knowledge, yet no u
Across the public sector, the conversation has shifted; we are no longer just talking about the potential of AI, we are already seeing the impact. While visionary leadership and cultural buy-in are cr
arXiv:2512.05439v2 Announce Type: replace Abstract: As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model
arXiv:2605.07111v1 Announce Type: cross Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational pla
arXiv:2605.06890v1 Announce Type: new Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagn
arXiv:2605.07098v1 Announce Type: new Abstract: Crash simulation is a cornerstone of modern vehicle development because it reduces the need for costly physical prototypes, accelerates safety-driven de
arXiv:2505.14113v3 Announce Type: replace Abstract: Most machine learning-based image segmentation models produce pixel-wise confidence scores that represent the model's predicted probability for each
arXiv:2605.06115v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs), trained primarily on English-centric data, frequently generate culturally inappropriate or misaligned resp
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:2603.04676v2 Announce Type: replace-cross Abstract: Multi-image reasoning remains a significant challenge for vision-language models (VLMs). We investigate a previously overlooked phenomenon: du
arXiv:2605.07821v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangle
arXiv:2605.07299v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) remain primarily reactive, failing to continuously perceive environments or proactively assist users
arXiv:2605.06840v1 Announce Type: new Abstract: Large language models (LLMs), especially reasoning models, generate extended chain-of-thought (CoT) reasoning that often contains explicit deliberation
arXiv:2605.07208v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used to brainstorm and evaluate research ideas, yet assessing such judgments is fundamentally difficult be
arXiv:2605.06755v1 Announce Type: cross Abstract: Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked.
arXiv:2510.22944v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a c
arXiv:2605.07305v1 Announce Type: cross Abstract: Most existing LLM diagnoses are evaluated on static, single-turn settings where complete patient information is provided upfront, an oversimplificatio
arXiv:2603.09652v3 Announce Type: replace Abstract: With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynami
arXiv:2603.24946v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on
arXiv:2601.07247v2 Announce Type: replace-cross Abstract: Learning models that can handle distribution shifts is a key challenge in domain generalization. Invariance learning, an approach that focuses
OpenAI launched DeployCo, a new service designed to assist businesses in building and deploying applications leveraging OpenAI's AI models and intelligence capabilities. The offering appears to focus
arXiv:2605.07687v1 Announce Type: new Abstract: Physics-based digital twins aim to predict the dynamics of real-world objects under interaction, enabling real-to-sim-to-real applications in robotics.
arXiv:2605.06987v1 Announce Type: new Abstract: Aligning large language models (LLMs) to human preferences typically relies on aggregating pooled feedback into a single reward model. However, this sta
arXiv:2602.04556v2 Announce Type: replace Abstract: Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output pr
arXiv:2605.07630v1 Announce Type: cross Abstract: When a phone-use agent avoids harm, does that show safety, or simply inability to act? Existing evaluations often cannot tell. A harmful outcome may b
arXiv:2605.07465v1 Announce Type: new Abstract: Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Exist
arXiv:2605.06353v2 Announce Type: replace Abstract: In a conversation, a helpful assistant must reliably follow user directives, even as they refine, modify, or contradict earlier requests. Yet most i
arXiv:2605.07186v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) benchmarks primarily focus on syntactically correct inputs, leaving a significant gap in evaluation on imperfect t
arXiv:2605.06175v2 Announce Type: replace Abstract: Vision-language-action (VLA) models inherit rich visual-semantic priors from pre-trained vision-language backbones, but adapting them to robotic con
arXiv:2605.07915v1 Announce Type: new Abstract: Tokenizers are a crucial component of latent diffusion models, as they define the latent space in which diffusion models operate. However, existing toke
arXiv:2605.05000v1 Announce Type: cross Abstract: Windows Component Object Model (COM) services run with elevated privileges and are widely accessible to authenticated users, making race conditions in
arXiv:2605.04128v1 Announce Type: cross Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing
arXiv:2605.05121v1 Announce Type: new Abstract: Automated mental health prediction using textual data has shown promising results with deep learning and large language models. However, deploying these
arXiv:2602.19651v2 Announce Type: replace-cross Abstract: Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at max
arXiv:2605.04503v1 Announce Type: new Abstract: Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key bench
arXiv:2601.19690v2 Announce Type: replace Abstract: Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing lon
arXiv:2605.04590v1 Announce Type: new Abstract: Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application
Hermes is an AI model developed by Nous Research that focuses on instruction-following and reasoning capabilities. Based on Nous Research's focus, this likely covers the model's architecture, performa