Zamba2-VL Technical Report
arXiv:2606.00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with
Knowledge catalogue
arXiv:2606.00390v1 Announce Type: cross Abstract: We present Zamba2-VL, a suite of vision-language models built on Zamba2, a hybrid language-model architecture combining Mamba2 state-space layers with
arXiv:2602.08964v2 Announce Type: replace-cross Abstract: Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals
arXiv:2605.30668v1 Announce Type: cross Abstract: Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including
arXiv:2605.30846v1 Announce Type: new Abstract: Object counting remains fragmented across domain-specific datasets and task formulations, despite rapid progress in generalist vision models. Existing c
arXiv:2605.30997v1 Announce Type: cross Abstract: When a learner faces a new task with few samples, it must leverage any available side information. In practice, this often comes in the form of model
arXiv:2602.16165v2 Announce Type: replace-cross Abstract: Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and del
arXiv:2605.31478v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate power-system analysis, but many utilities and energy-research labs require on-premise s
arXiv:2605.30778v1 Announce Type: new Abstract: Long-horizon planning for non-prehensile robot manipulation is challenging due to underactuated and discontinuous interactions. We propose a hierarchica
arXiv:2605.31142v1 Announce Type: cross Abstract: Large-scale multilingual text embedding models play crucial role in both research and industry, yet their behavior in language-specific, multi-task se
arXiv:2602.12192v3 Announce Type: replace Abstract: Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to es
arXiv:2605.31048v1 Announce Type: new Abstract: Recent crack segmentation methods often follow generic semantic segmentation designs, using stronger backbones, hybrid CNN-Transformer-Mamba encoders, a
arXiv:2605.31183v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have been seen as a promising avenue for exploring the internals of Large Language Models (LLMs) and for steering model out
arXiv:2605.30506v1 Announce Type: cross Abstract: Global localization in geometrically aliased, quasi-static environments such as grocery stores, offices, schools, and hospitals poses a significant ch
May ships trace-based evaluation for any agent on any cloud, Grok 4.3 and DeepSeek V4 in the model catalog, GPT-5 Reinforcement Fine-Tuning at gated GA, three Microsoft Research on-device agent models
arXiv:2605.30202v1 Announce Type: new Abstract: Looped transformers apply a shared block multiple times and have emerged as a parameter-efficient route to scaling compute in language models. However,
arXiv:2605.29488v1 Announce Type: cross Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are
arXiv:2605.21739v2 Announce Type: replace Abstract: Emotional intelligence (EI), the ability to perceive, understand, and respond appropriately to others' emotional states, is central to human communi
arXiv:2605.29705v1 Announce Type: new Abstract: Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large langua
arXiv:2605.29901v1 Announce Type: cross Abstract: Large language models (LLMs) can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using me
arXiv:2605.29339v1 Announce Type: new Abstract: With the rapid advancement of multimodal large language models (MLLMs), models have demonstrated increasingly powerful multimodal capabilities. However,
arXiv:2605.29637v1 Announce Type: new Abstract: Large language models recall knowledge reliably in English but often fail on the same query posed in a lower-resourced language -- a crosslingual consis
arXiv:2605.29394v1 Announce Type: new Abstract: While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We
arXiv:2605.29762v1 Announce Type: new Abstract: Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inconsistencies under complex geometric transformation
arXiv:2605.29661v1 Announce Type: new Abstract: Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object
arXiv:2605.29578v1 Announce Type: new Abstract: Tourist mobility poses a distinct challenge for urban transportation planning. Unlike resident commuting, tourist travel is largely non-routine, attract
arXiv:2605.28910v1 Announce Type: cross Abstract: Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect stat
arXiv:2605.29782v1 Announce Type: cross Abstract: Reinforcement learning (RL) refines large language models (LLMs) by directly optimizing model behavior through reward signals. While accurate state va
arXiv:2605.29473v1 Announce Type: cross Abstract: Language models are increasingly being deployed for conversational support in informal caregiving contexts, where interactions often extend beyond inf
NVIDIA has released a corrected version of DeepSeek-V4-Pro-NVFP4, a quantized model variant optimized for NVIDIA hardware using NV-FP4 (NVIDIA's 4-bit floating-point format). The model is available on
arXiv:2511.04934v3 Announce Type: replace Abstract: Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing
arXiv:2605.29765v1 Announce Type: new Abstract: We introduce MMTM, a modular pipeline for topic discovery in long-form video that integrates speech recognition, audio and visual embeddings, and BERTop
arXiv:2506.04602v4 Announce Type: replace-cross Abstract: The burgeoning growth of the esports and multiplayer online gaming community has highlighted the critical importance of evaluating the Most Va
arXiv:2510.08535v2 Announce Type: replace-cross Abstract: Diffusion models are central to generative modeling and have been adapted to graphs by diffusing adjacency matrix representations. The challen
arXiv:2605.29729v1 Announce Type: new Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming
arXiv:2605.29425v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promise in traffic signal control (TSC). However, its reliance on predefined states limits responsiveness to obser
arXiv:2605.30166v1 Announce Type: cross Abstract: LLM-driven social bots can generate fluent, human-like text, reducing the discriminative advantage of content-based detection alone. However, coordina
arXiv:2605.29236v1 Announce Type: new Abstract: Alarm fatigue in intensive care units (ICUs) is a well documented patient safety crisis. Clinical monitors generate 350 or more alarms per patient per d
arXiv:2602.08013v2 Announce Type: replace Abstract: The rapid adoption of large language models (LLMs) in digital health has been driven by a 'scaling-first' philosophy, i.e., the assumption that clin
arXiv:2605.28966v1 Announce Type: new Abstract: Large language model (LLM) leaderboards rank AI models using standardized benchmarks and have become highly visible across computer science, despite kno
arXiv:2605.28440v1 Announce Type: new Abstract: DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loo
Since its inception over 20 years ago, Google has used Site Reliability Engineering (SRE) to keep services like Search, Gmail, Maps, YouTube and Google Cloud reliable and highly available, adhering to
arXiv:2605.28659v1 Announce Type: new Abstract: Biological foundation models have shown strong performance in single-cell representation learning by applying transformer architectures directly to gene
Anthropic shipped Claude Opus 4.8 today. My favourite thing about it is this note in the release announcement: Users will find Opus 4.8 to be a modest but tangible improvement on its predecessor. Ther
arXiv:2605.28167v1 Announce Type: new Abstract: Text-to-image diffusion models, which are theoretically equivalent to score-based generative models, generate images through a multi-step denoising proc
arXiv:2605.27849v1 Announce Type: cross Abstract: Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming
arXiv:2605.27433v1 Announce Type: cross Abstract: With the increasing complexity of collaboration among various social entities and user demands, the factors affecting the stable development of the da
arXiv:2605.27984v1 Announce Type: cross Abstract: Speech language models (SpeechLMs) have achieved substantial progress by extending large language models (LLMs) to the speech modality. However, Speec
arXiv:2605.27400v1 Announce Type: cross Abstract: The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around aca
arXiv:2304.12986v3 Announce Type: replace-cross Abstract: The development of large-scale Chinese language models is flourishing, yet there is a lack of corresponding capability assessments. Therefore,
arXiv:2605.28035v1 Announce Type: new Abstract: In recent years, Multi-Talker Audio-Video Generation (MTAVG) models have shown promising performance on fundamental metrics such as lip-sync and audio-v
arXiv:2605.28722v1 Announce Type: new Abstract: Representation intervention has emerged as a promising paradigm for aligning large language models toward desired behaviors without modifying model weig
arXiv:2605.28579v1 Announce Type: new Abstract: Large language models (LLMs) have recently advanced text-driven 3D generation, yet Text-to-CAD remains far from supporting industrial product design. Ex
arXiv:2605.27382v1 Announce Type: cross Abstract: A key promise of pluralistic AI is behavioral adaptation: persona prompts like 'be creative' or 'be thorough' let systems respect diverse user values
arXiv:2605.27690v1 Announce Type: new Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long be
arXiv:2602.11460v2 Announce Type: replace Abstract: Large language models (LLMs) have shown great potential for healthcare applications. However, existing evaluation benchmarks provide minimal coverag
arXiv:2602.13626v3 Announce Type: replace Abstract: The expanding integration of Large Language Models (LLMs) into recommender systems poses critical challenges to evaluation reliability. This paper i
arXiv:2605.26279v1 Announce Type: new Abstract: Constraint Acquisition (CA) and related research on the validation and enhancement of Mathematical Programming (MP) models from domain knowledge artifac
arXiv:2605.26935v1 Announce Type: new Abstract: Large language models have achieved strong performance across many NLP tasks, yet Urdu remains comparatively underexplored due to limited resources and
arXiv:2605.26785v1 Announce Type: cross Abstract: Post-trained LLMs are often optimized to align responses with human preferences, making them safe, polite, and conversationally appropriate. In advers
arXiv:2605.26230v1 Announce Type: new Abstract: Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typica