Knowledge catalogue
arXiv:2502.04416v3 Announce Type: replace-cross Abstract: Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consu
API is Available Today! 🔹 Keep base_url, just update model to deepseek-v4-pro or deepseek-v4-flash. 🔹 Supports OpenAI ChatCompletions & Anthropic APIs. 🔹 Both models support 1M context & dual modes (T
arXiv:2604.21083v1 Announce Type: cross Abstract: Third-party Large Language Model (LLM) API gateways are rapidly emerging as unified access points to models offered by multiple vendors. However, the
arXiv:2604.21573v1 Announce Type: new Abstract: Spatial transcriptomics (ST) enables spatially resolved gene profiling but remains expensive and low-throughput, limiting large-cohort studies and routi
arXiv:2604.21354v1 Announce Type: new Abstract: Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In
arXiv:2509.22321v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neu
arXiv:2604.20920v1 Announce Type: new Abstract: Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include K
arXiv:2604.20902v1 Announce Type: cross Abstract: While standard flow-matching models transport noise to data uniformly, incorporating an explicit generation order - specifically, establishing coarse,
Vercel announced the availability of GPT-5.5 through its AI Gateway service, expanding the model options developers can access through the platform. This integration allows developers to leverage Open
arXiv:2604.21760v1 Announce Type: new Abstract: Deepfake detection research has largely converged on deep learning approaches that, despite strong benchmark performance, offer limited insight into wha
arXiv:2604.21011v1 Announce Type: new Abstract: Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one's head or tapping fingers. Such subtle actions are essential fo
arXiv:2604.20858v1 Announce Type: cross Abstract: Sequential recommendation has rapidly advanced in click-through rate prediction due to its ability to model dynamic user interests. A key challenge, h
arXiv:2604.20867v1 Announce Type: cross Abstract: Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible:
arXiv:2604.21160v1 Announce Type: new Abstract: Point-Vision-Language Models promise to empower embodied agents with executable spatial reasoning, yet they frequently succumb to geometric hallucinatio
arXiv:2604.21776v1 Announce Type: new Abstract: Precise camera control for reshooting dynamic videos is bottlenecked by the severe scarcity of paired multi-view data for non-rigid scenes. We overcome
arXiv:2604.21478v1 Announce Type: new Abstract: Nowadays, visual data forgery detection plays an increasingly important role in social and economic security with the rapid development of generative mo
arXiv:2604.21930v1 Announce Type: new Abstract: Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal partitioning. We argue that
@benswerd there are tradeoffs but we've spoken to folks doing both inside and outside and the split is pretty much 50:50 in our experience. I've found @hwchase17's list of tradeoffs the most accurate
Confidently wrong is worse than just wrong. When an AI searches one giant knowledge base for everything, it finds something—and serves it up like it's the answer. That's not a model problem. That's a
arXiv:2604.20817v1 Announce Type: cross Abstract: Language models trained on natural text learn to represent numbers using periodic features with dominant periods at T=2, 5, 10. In this paper, we iden
arXiv:2601.00911v3 Announce Type: replace-cross Abstract: Automated negotiations in insurance and business-to-business (B2B) commerce encounter substantial challenges. Current systems force a trade-of
arXiv:2604.19781v1 Announce Type: cross Abstract: Automated scoring of student work at scale requires balancing accuracy against cost and latency. In 'cascade' systems, small language models (LMs) han
arXiv:2604.01965v2 Announce Type: replace-cross Abstract: Scientific knowledge discovery increasingly relies on large language models, yet many existing scholarly assistants depend on proprietary syst
arXiv:2604.20281v1 Announce Type: new Abstract: With the rapid advancement of intelligent driving and remote sensing, oriented object detection has gained widespread attention. However, achieving high
arXiv:2604.19794v1 Announce Type: new Abstract: Rough set theory models uncertainty by approximating target concepts through lower and upper sets induced by indiscernibility, or more generally, by gra
arXiv:2604.20452v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as c
arXiv:2508.09958v3 Announce Type: replace Abstract: As large language models (LLMs) become increasingly popular, there is a growing need to predict which out of a set of LLMs will yield a successful a
arXiv:2604.20268v1 Announce Type: new Abstract: Background: Osteoporosis and osteopenia are often undiagnosed until fragility fractures occur. Dual-energy X-ray absorptiometry (DXA) is the reference s
arXiv:2604.20594v1 Announce Type: new Abstract: Retinal laser speckle contrast imaging (LSCI) is a noninvasive optical modality for monitoring retinal blood flow dynamics. However, conventional tempor
arXiv:2604.20145v1 Announce Type: cross Abstract: Cloud data warehouses bill compute based on slot-time consumed. In shared multi-tenant environments, query cost is highly variable and hard to estimat
arXiv:2604.19807v1 Announce Type: new Abstract: In multi-criteria graph traversal, paths are compared via Pareto dominance, an ordering that identifies which paths are non-dominated, but says nothing
arXiv:2604.19829v1 Announce Type: new Abstract: Tactile graphics require careful expert validation before reaching blind and visually impaired (BVI) learners, yet existing datasets provide only coarse
arXiv:2511.03690v2 Announce Type: replace-cross Abstract: Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task
arXiv:2604.19756v1 Announce Type: cross Abstract: Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse p
arXiv:2511.08277v2 Announce Type: replace-cross Abstract: Learning-based inertial odometry has achieved remarkable progress in pedestrian navigation. However, extending these methods to quadruped robo
arXiv:2604.18806v1 Announce Type: new Abstract: 3D-IC netlist partitioning is commonly optimized using proxy objectives, while final PPA is treated as a costly evaluation rather than an optimization s
arXiv:2604.19011v1 Announce Type: new Abstract: Trajectory Optimization (TO) solvers exploit known system dynamics to compute locally optimal trajectories through iterative improvements. A downside is
arXiv:2604.18781v1 Announce Type: new Abstract: Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice, anisotropic acquisitions prevalent in routine clinical practice.
arXiv:2604.02923v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), particularly those employing Mixture-of-Experts (MoE) architectures, have achieved remarkable capabilities acros
arXiv:2604.19566v1 Announce Type: cross Abstract: Reliable biomedical and clinical retrieval requires more than strong ranking performance: it requires a practical way to find systematic model failure
arXiv:2602.05993v2 Announce Type: replace-cross Abstract: Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and
arXiv:2604.19341v1 Announce Type: cross Abstract: Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively
arXiv:2604.19669v1 Announce Type: new Abstract: Enforcing constraint satisfaction in neural network outputs is critical for safety, reliability, and physical fidelity in many control and decision-maki
LiteParse: our open-source, layout-aware PDF parser for AI agents. The secret? Grid projection. Instead of heavy ML layout models or flat text extraction, it projects text onto a monospace grid so ali
arXiv:2602.12708v2 Announce Type: replace Abstract: Vertical Federated Learning (VFL) has emerged as a critical paradigm for collaborative model training in privacy-sensitive domains such as finance a
arXiv:2604.18712v1 Announce Type: new Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive sig
arXiv:2604.19343v1 Announce Type: cross Abstract: Memristive devices present a promising foundation for next-generation information processing by combining memory and computation within a single physi
arXiv:2601.02993v4 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) has become a key paradigm for reducing factual hallucinations in Large Language Models (LLMs), yet little is kn
The Never Ending Lore of Harness w/@Vtrivedy10⚡️ Viv brought some amazing perspective around harness design, evals, file systems, RL Envs and so much. 0:00:00 - INTRO 0:03:30 - PhD at Temple Universit
arXiv:2604.19218v1 Announce Type: new Abstract: Learning identity-discriminative representations with multi-scene generality has become a critical objective in person re-identification (ReID). However
arXiv:2510.06860v2 Announce Type: replace-cross Abstract: AC Optimal Power Flow (ACOPF) is computationally intensive for large-scale grids, often requiring prohibitive solution times with conventional
Succeeding in the agentic era requires a transformation in your data strategy: moving from human-scale to agent-first workloads, evolving from reactive intelligence to proactive action, and shifting f
At Google Cloud Next, we’re announcing a range of compute capabilities to enable your core general purpose and AI workloads for the agentic world with higher performance and lower costs. Why it matter
arXiv:2604.16879v1 Announce Type: new Abstract: With the rapid development of generative models and multimodal content editing technologies, the key challenge faced by synthetic image detection (SID)
arXiv:2604.17325v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated conte
arXiv:2604.16622v1 Announce Type: new Abstract: Backchannels (e.g., `yeah', `mhm', and `right') are short, non-interruptive feedback signals whose lexical form and prosody jointly convey pragmatic mea
arXiv:2604.17188v1 Announce Type: new Abstract: Multi-role dialogue summarization requires modeling complex interactions among multiple speakers while preserving role-specific information and factual
arXiv:2604.17221v1 Announce Type: cross Abstract: Selective State Space Models (SSMs), notably Mamba, employ diagonal state transitions that limit both memory retention and bilinear computational capa
arXiv:2604.16893v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large languag
arXiv:2510.16756v2 Announce Type: replace-cross Abstract: Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and