Knowledge catalogue
fun off-the-cuff harness + agent engineering sesh with @dexhorthy @vaibcode @GeoffreyHuntley - a lot of good harness/agent design we’re doing today is still good context engineering, remember tool cal
arXiv:2604.16406v1 Announce Type: cross Abstract: Realistic highway simulation is critical for scalable safety evaluation of autonomous vehicles, particularly for interactions that are too rare to stu
arXiv:2604.16749v1 Announce Type: cross Abstract: Audio deepfakes pose a significant security threat, yet current state-of-the-art (SOTA) detection systems do not generalize well to realistic in-the-w
arXiv:2604.17730v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging d
arXiv:2512.21510v2 Announce Type: replace-cross Abstract: Real-world multi-view data often exhibit highly inconsistent missing patterns, posing significant challenges for incomplete multi-view cluster
arXiv:2501.12281v2 Announce Type: replace Abstract: Given a partially observed road network, how can we predict the traffic state of interested unobserved locations? Traffic prediction is crucial for
arXiv:2604.16503v1 Announce Type: new Abstract: Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether
arXiv:2506.01942v2 Announce Type: replace Abstract: Training large neural networks on large-scale datasets requires substantial computational resources, particularly for dense prediction tasks such as
arXiv:2604.18486v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature
arXiv:2602.06663v2 Announce Type: replace Abstract: Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their
arXiv:2510.16054v2 Announce Type: replace-cross Abstract: When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send th
arXiv:2604.18112v1 Announce Type: new Abstract: In recent years, multimodal multidomain fake news detection has garnered increasing attention. Nevertheless, this direction presents two significant cha
arXiv:2604.16683v1 Announce Type: cross Abstract: Imitation learning has enabled robots to acquire complex visuomotor manipulation skills from demonstrations, but deployment failures remain a major ob
arXiv:2604.17301v1 Announce Type: new Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most
arXiv:2604.16358v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploi
arXiv:2604.18476v1 Announce Type: new Abstract: Camera-only 3D object detection has emerged as a cost-effective and scalable alternative to LiDAR for autonomous driving, yet existing methods primarily
arXiv:2604.18580v1 Announce Type: cross Abstract: Modern sequence models are dominated by Transformers, where self-attention mixes information from the visible context in an input-dependent way. Howev
arXiv:2604.17782v1 Announce Type: new Abstract: Zero-shot EEG-to-image retrieval aims to decode perceived visual content from electroencephalography (EEG) by aligning neural responses with pretrained
arXiv:2604.17114v1 Announce Type: new Abstract: Frontier large language models generate clinically accurate outputs, but their citations are often fabricated. We term this the Provenance Gap. We teste
arXiv:2509.18060v2 Announce Type: replace Abstract: Tibetan is a low-resource language with limited parallel speech corpora spanning its three major dialects (U-Tsang, Amdo, and Kham), limiting progre
arXiv:2604.18473v1 Announce Type: new Abstract: Extending a fully post-trained language model with new domain capabilities is fundamentally limited by monolithic training paradigms: retraining from sc
arXiv:2604.18539v1 Announce Type: new Abstract: This paper studies how empirical dialogue-flow statistics can be incorporated into Next Dialogue Act Prediction (NDAP). A KL regularization term is prop
We are excited to have @FireworksAI_HQ as a day 0 launch partner for Kimi K2.6! Their inference and fine-tuning platform is fast, reliable, and scales well under real production load, making it easy t
arXiv:2604.17375v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have substantially enhanced their ability across multimodal video understanding benchmarks spanning tem
arXiv:2604.17422v1 Announce Type: new Abstract: Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of proces
arXiv:2604.15414v1 Announce Type: cross Abstract: Continual reinforcement learning must balance retention with adaptation, yet many methods still rely on single-model preservation, committing to one e
arXiv:2604.16099v1 Announce Type: new Abstract: Tables condense key transactional and administrative information into compact layouts, but practical extraction requires more than text recognition: sys
arXiv:2604.16279v1 Announce Type: new Abstract: Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse s
arXiv:2604.15495v1 Announce Type: new Abstract: Navigating complex, densely packed environments like retail stores, warehouses, and hospitals poses a significant spatial grounding challenge for humans
arXiv:2604.16264v1 Announce Type: new Abstract: Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, whe
arXiv:2602.07303v3 Announce Type: replace-cross Abstract: Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions w
arXiv:2604.15760v1 Announce Type: new Abstract: We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM id
arXiv:2604.15917v1 Announce Type: new Abstract: Instruction guided image editing has advanced substantially with recent generative models, yet it still fails to produce reliable results across many se
Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often
arXiv:2604.15890v1 Announce Type: new Abstract: Multi-UAV inspection missions require spare drones to replace active drones during recharging cycles. Existing fleet-sizing approaches often assume stea
arXiv:2504.00966v2 Announce Type: replace Abstract: This article studies the time-optimal path planning problem for a convexified Reeds-Shepp (CRS) vehicle on a unit sphere, capable of both forward an
arXiv:2604.15827v1 Announce Type: cross Abstract: Conventional information retrieval is concerned with identifying the relevance of texts for a given query. Yet, the conventional definition of relevan
We’re launching Kimi K2.6 on Fireworks as a Day-0 launch partner! K2.5 was the base for standout models like @Cursor’s Composer 2 and was the most popular model on our training platform. K2.6 on Firew
arXiv:2604.15764v1 Announce Type: cross Abstract: Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8imes inference s
arXiv:2601.03746v3 Announce Type: replace Abstract: As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their beh
arXiv:2604.15376v1 Announce Type: cross Abstract: Multi-step zoom-in pipelines are widely used for GUI grounding, yet the intermediate predictions they produce are typically discarded after coordinate
Introducing OpenMythos An open-source, first-principles theoretical reconstruction of Claude Mythos, implemented in PyTorch. The architecture instantiates a looped transformer with a Mixture-of-Expert
LangChain Community Spotlight: Saving $1M in LLM Costs 💰 Gustaf, an AI Engineer, shows how he reduced a production RAG chatbot's costs by 90% and improved latency by 82% through caching, intelligent r
LangChain Community Spotlight: LangAlpha 💼 A coding tool built for Wall Street professionals, bringing AI-powered development to financial workflows. Check it out: https://news.ycombinator.com/from?si
arXiv:2601.20352v3 Announce Type: replace Abstract: The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and comple
arXiv:2604.13959v1 Announce Type: new Abstract: As AI moves from data centers to robots and wearables, scaling ever-larger models becomes insufficient. Physical AI operates under tight latency, energy
arXiv:2604.13048v1 Announce Type: cross Abstract: Modern cloud-native platforms expose thousands of time series metrics through systems like Prometheus, yet formulating correct queries in domain-speci
arXiv:2604.14884v1 Announce Type: new Abstract: Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex bac
in 1996 mitzenmacher showed that sampling two backends and picking the better one drops max load exponentially vs. random selection one extra comparison. that's the whole trick we built pinecone assis
arXiv:2601.14053v2 Announce Type: replace-cross Abstract: The field of artificial intelligence has undergone a revolution from foundational Transformer architectures to reasoning-capable systems appro
arXiv:2604.14593v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate increasingly sophisticated affective capabilities, the internal mechanisms by which they process complex
arXiv:2505.18129v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is becoming an important direction for post-training vision-language models (VLMs), but public training methodolog
arXiv:2604.14634v1 Announce Type: new Abstract: Multiple choice evaluation is widely used for benchmarking large language models, yet near ceiling accuracy in low option settings can be sustained by s
arXiv:2604.13757v1 Announce Type: new Abstract: The next generation of autonomous AI systems will be constrained not only by model capability, but by how intelligence is structured across heterogeneou
arXiv:2602.13529v2 Announce Type: replace-cross Abstract: Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-
arXiv:2604.15271v1 Announce Type: new Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decisio
arXiv:2604.14399v1 Announce Type: new Abstract: Autonomous on-orbit servicing demands embodied agents that perceive through visual sensors, reason about 3D spatial situations, and execute multi-phase
Real-time threat intelligence company Team Cymru Inc. today announced the launch of Total Insights Feed, a unified threat intelligence platform that is designed to replace legacy indicator list-based
arXiv:2604.14414v1 Announce Type: new Abstract: Turn-level metrics are widely used to evaluate properties of multi-turn human-LLM conversations, from safety and sycophancy to dialogue quality. However
arXiv:2604.13694v1 Announce Type: new Abstract: Mechanistic interpretability seeks to localize model behavior to the internal components that causally realize it. Prior work has advanced activation-sp