Knowledge catalogue
arXiv:2609.18688v1 Announce Type: cross Abstract: AI models for multimodal medical imaging must balance modality-specific specialization with cross-modal shared representations, a trade-off that pure
arXiv:2609.18548v1 Announce Type: cross Abstract: Egocentric motion forecasting has primarily focused on hands and manipulated objects, leaving future human head motion comparatively underexplored. Du
arXiv:2609.18680v1 Announce Type: new Abstract: Contextual ASR can benefit from semantic cues or from target words explicitly provided in the context. We introduce HearInContext, a Mandarin--English b
arXiv:2609.18598v1 Announce Type: cross Abstract: Self-driving laboratories can explore synthesis conditions autonomously, but their decision-making layer is typically a black-box optimizer, and the o
Important paper on improving agent coordination. On normal tasks, this work shows agents caused harm 0 to 5% of the time. After receiving an unsafe trajectory from another agent, that rose to 40 to 95
arXiv:2609.17777v1 Announce Type: cross Abstract: AI and large language models can recover clinically meaningful features from electronic health records (EHRs), but predictive usefulness does not esta
arXiv:2609.18971v1 Announce Type: new Abstract: Surgical phase recognition maps each video frame to a clinically meaningful workflow phase, supporting context-aware assistance, documentation, and post
arXiv:2609.18578v1 Announce Type: new Abstract: Pathologists diagnose diseases by first locating suspicious tissue and then examining it at higher magnification, whereas self-supervised vision transfo
arXiv:2609.19101v1 Announce Type: new Abstract: As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model represent
arXiv:2609.18898v1 Announce Type: new Abstract: Training-free weighted aggregation is widely used to lift 2D semantic features onto 3D Gaussians for open-vocabulary scene understanding, yet its theore
OpenAI: OpenAI launches Astra for Law, combining GPT-6 Astra with a legal search index and instructions for legal analysis and writing, initially for select law firms — Our most powerful model, config
arXiv:2609.17846v1 Announce Type: cross Abstract: Autonomous research agents aim to automate scientific workflows, from proposing ideas to conducting experiments and analyzing results. Yet current AI
arXiv:2609.19077v1 Announce Type: cross Abstract: Formal explainability provides mathematically grounded justifications for individual predictions. However, abductive explanations often exceed human c
arXiv:2509.16079v2 Announce Type: replace Abstract: Unsteady aerodynamic effects can have a profound impact on aerial vehicle flight performance, especially during agile maneuvers and in complex aerod
arXiv:2609.17537v1 Announce Type: new Abstract: We ask whether relation-type information (e.g., capital-of) and entity-specific information (e.g., France to Paris) become causally active at the final-
arXiv:2609.18708v1 Announce Type: cross Abstract: In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the
arXiv:2609.18442v1 Announce Type: new Abstract: Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We in
arXiv:2609.19134v1 Announce Type: new Abstract: Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conv
arXiv:2609.18310v1 Announce Type: new Abstract: We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 3
arXiv:2609.18562v1 Announce Type: new Abstract: Track 2 of the AI City Challenge 2026 requires both visual question answering (VQA) and traffic event description generation under a challenging synthet
arXiv:2609.19119v1 Announce Type: new Abstract: Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes i
arXiv:2609.18525v1 Announce Type: new Abstract: Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses
arXiv:2609.17984v1 Announce Type: new Abstract: Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by reca
arXiv:2609.18769v1 Announce Type: new Abstract: Correctly answering a question grounded in normative documents often depends on information outside any single passage: whether the retrieved document i
arXiv:2609.18521v1 Announce Type: cross Abstract: Speech retrieval has become increasingly important as spoken content continues to grow across meetings, lectures, podcasts, and videos. Existing bench
arXiv:2609.17989v1 Announce Type: cross Abstract: Large language models (LLMs) now serve as conversational shopping assistants on platforms that also sell advertising. These AI agents face a conflict
arXiv:2609.16464v1 Announce Type: new Abstract: The clinical management of autism spectrum disorder (ASD) faces a bottleneck in early screening, mainly because trained specialists are scarce and conve
arXiv:2609.16023v1 Announce Type: new Abstract: Medical evaluation is shifting from static option-based questioning to realistic clinical scenarios with open-ended output modes. Grading these at scale
arXiv:2501.09166v2 Announce Type: replace-cross Abstract: Pretrained Transformers keep what they learned in their weights and lose what they observe once a session ends. The first version of this pape
arXiv:2609.17056v1 Announce Type: cross Abstract: Current predictive turn-taking models (PTTMs) achieve strong performance on benchmarks with controlled acoustic conditions and clean audio signals. Th
Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star
arXiv:2609.16664v1 Announce Type: new Abstract: Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contr
arXiv:2609.17263v1 Announce Type: new Abstract: Assembly Sequence Planning (ASP) remains a challenging problem due to its combinatorial nature, making exhaustive planning approaches impractical for co
arXiv:2609.16768v1 Announce Type: new Abstract: IMU-based human activity recognition (HAR) enables continuous, privacy-friendly monitoring of daily activities using wearable sensors. However, building
arXiv:2601.18493v2 Announce Type: replace Abstract: Vision--language models (VLMs) show promise for disaster-response remote sensing, but existing benchmarks mainly emphasize scene-level or damage-cen
arXiv:2609.17360v1 Announce Type: new Abstract: Full-duplex spoken dialogue systems must distinguish interruptions that require yielding the floor from backchannels that permit continued speaking. Exi
arXiv:2609.17439v1 Announce Type: cross Abstract: Reliable quantum engineering is essential for turning quantum phenomena into practical technologies. As quantum platforms grow in scale and complexity
arXiv:2609.16811v1 Announce Type: new Abstract: Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity
Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess
arXiv:2609.17181v1 Announce Type: cross Abstract: The analysis and classification of cultural heritage architectural styles remain challenging due to the complexity of visual images of buildings, whic
arXiv:2609.15999v1 Announce Type: new Abstract: Accessing legal information in Nepal is difficult due to complex terminology, limited resources, and misinformation. We introduce an AI-powered legal as
arXiv:2609.16057v1 Announce Type: cross Abstract: Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Exist
arXiv:2609.15992v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have rendered them necessary for Natural Language Processing (NLP) tasks, and their high inference cost
arXiv:2609.16995v1 Announce Type: new Abstract: Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such i
arXiv:2609.17251v1 Announce Type: new Abstract: We introduce a simple architectural modification to decoder-only transformers: a persistent recurrent state that observes hidden representations via cro
arXiv:2609.17211v1 Announce Type: new Abstract: Video anomaly detection (VAD) aims to localize anomalous events in untrimmed videos. Vision-language models (VLMs) provide rich visual understanding for
arXiv:2609.16627v1 Announce Type: new Abstract: Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because rel
Setup for one long agentic coding session (tools + vision) on a single 5090: Qwen3.8-27B RVN Heretic (ARA abliterated) at Q6_K, 159744 context, 1 slot, q8_0 K/V, DFlash2 speculative decoding, vision p
arXiv:2505.13388v4 Announce Type: replace-cross Abstract: Reward models are essential for aligning language model outputs with human preferences, yet existing approaches often lack both controllabilit
arXiv:2609.16639v1 Announce Type: new Abstract: Continual post-training of large multimodal models should add new capabilities while preserving those from pre-training, and the two goals pull in oppos
arXiv:2609.16427v1 Announce Type: new Abstract: This paper presents a Belarusian-specific data-cleaning pipeline and fine-tuning for English-Belarusian machine translation. Our cleaning pipeline disti
arXiv:2609.16053v1 Announce Type: cross Abstract: Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new info
arXiv:2609.16145v1 Announce Type: new Abstract: We study a practical question: can a small correction module fix errors in a frozen language model's outputs without degrading its base capabilities? We
arXiv:2609.17109v1 Announce Type: new Abstract: A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefil
arXiv:2609.17414v1 Announce Type: new Abstract: Text-conditioned latent diffusion models perform strongly in video generation and are promising backbones for robotic applications. However, existing ap
arXiv:2609.16532v1 Announce Type: new Abstract: Continued pretraining (CPT) with data augmentation such as paraphrasing can store inside a large language model (LLM) the knowledge of a small source co
arXiv:2609.17107v1 Announce Type: new Abstract: Generative AI promises natural language access to the massive numerical telemetry of data centers and Industry 4.0 installations, yet text-to-query and
the risks WERE foreseeable; i foresaw them. repeatedly, focusing specifically on the risks of LLMs and cybersecurity. happy to provide receipts on request. I’m not a lawyer, but Sam Altman and Dario A
arXiv:2609.16748v1 Announce Type: new Abstract: Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) ha
arXiv:2609.16059v1 Announce Type: new Abstract: Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fine-T