CompanyAnthropic7 recent entries22 Apr 2026CASS: Nvidia to AMD Transpilation with Data, Models, and BenchmarkarXiv:2505.16968v4 Announce Type: replace-cross Abstract: Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We intro→24 Apr 2026Kernel-Smith: A Unified Recipe for Evolutionary Kernel OptimizationarXiv:2603.28342v2 Announce Type: replace Abstract: We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary a
CompanyOpenAI5 recent entries9 Jun 2026Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)arXiv:2606.07608v1 Announce Type: cross Abstract: We present a systematic study of fine-tuning OpenAI's Whisper large-v3 for Swiss German ASR, using 1,367 hours of broadcast speech paired with Standar→11 Aug 2026Who Verifies the Benchmark? Decentralizing Trust in Large Language Model EvaluationarXiv:2608.07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims tha→19 Aug 2026Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot SeearXiv:2608.17744v1 Announce Type: new Abstract: Take three frontier mixture-of-experts models (Alibaba, OpenAI, NVIDIA; 3.6-4.0B active parameters each) and fine-tune them to reason in a low-resource →16 Sept 2026Enhancing Law-Enforcement Audio Transcription: A LoRA-Based Adaptation of Whisper for BWC FootagearXiv:2607.27245v2 Announce Type: replace-cross Abstract: Modern policing faces a 'visibility paradox' where law enforcement agencies possess petabytes of Body-Worn Camera (BWC) footage that remains l→25 Sept 2026TRACE: Interactive Bi-Directional Tracing of Monochrome Cables Amid ClutterarXiv:2609.29103v1 Announce Type: new Abstract: Accurate state estimation (tracing) of Deformable Linear Objects (DLOs) such as cables is a critical challenge for data centers, manufacturing, construc
CompanyGoogle6 recent entries24 Apr 2026Kernel-Smith: A Unified Recipe for Evolutionary Kernel OptimizationarXiv:2603.28342v2 Announce Type: replace Abstract: We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary a→6 Jun 2026Evaluation of LLMs for Mathematical Formalization in LeanarXiv:2606.05632v1 Announce Type: new Abstract: Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically. We provide a com→10 Jul 2026Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond ImitationarXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m→24 Jul 2026Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token TimingarXiv:2607.20723v1 Announce Type: cross Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. L→19 Aug 2026Key-Frame Reasoning with SAM3: Third Place Solution for the MeViS-Text Track of the 8th LSVOS ChallengearXiv:2608.17279v1 Announce Type: new Abstract: This report presents a two-stage, training-free solution for the MeViS-Text track of the 8th LSVOS Challenge. The task requires a model to localize and →1 Sept 2026Distributional Validity and Calibration of a Korean Synthetic Persona Panel for Digital and AI Service Use: A Secondary-Data Validation Against the Korea Media Panel SurveyarXiv:2608.28615v1 Announce Type: cross Abstract: Synthetic personas based on large language models (LLMs) are increasingly proposed as substitutes for human survey respondents, yet systematic validat
CompanyMeta8 recent entries25 Sept 2026Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context InferencearXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o→28 Sept 2026The KV Cache Is the New Memory WallarXiv:2609.30854v1 Announce Type: cross Abstract: Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model wei→29 Sept 2026PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate AttentionarXiv:2609.33746v1 Announce Type: new Abstract: At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by→2 Oct 2026AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF ComputingarXiv:2610.00465v1 Announce Type: cross Abstract: Next-generation large language models (LLMs) are expanding from the cloud to ubiquitous edge devices. However, edge devices typically either lack the →6 Oct 2026StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMsarXiv:2610.05977v1 Announce Type: new Abstract: Serving a large language model (LLM) across a fleet of deployments requires several weight-precision operating points. Multi-precision formats serve the→12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still →14 Oct 2026Towards Green AI: Evaluating Energy Efficiency for Quantized LLM InferencearXiv:2610.17531v1 Announce Type: new Abstract: While it is known that quantization of large language models (LLMs) reduces memory usage via lower-bit weights, studies quantifying the resulting impact→14 Oct 2026Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language ModelsarXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons
CompanyMistral8 recent entries24 Apr 2026Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication ReconciliationarXiv:2604.21076v1 Announce Type: cross Abstract: Medication reconciliation at clinical handoffs is a high-stakes, error-prone process. Large language models are increasingly proposed to assist with t→15 May 2026Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative StudyarXiv:2605.14890v1 Announce Type: new Abstract: Foundation models tokenize Ukrainian legal text with vastly different efficiency, yet no systematic comparison exists for this domain. We benchmark seve→10 Jun 2026Alignment Collapse Under KV Cache Quantization: Diagnosis and MitigationarXiv:2606.09864v1 Announce Type: cross Abstract: Key-value (KV) cache quantization is widely used to reduce Large Language Model (LLM) inference memory, yet existing evaluations solely focus on measu→23 Jul 2026Benchmarking Confidential GPU Inference on NVIDIA H100 under Intel TDXarXiv:2607.19353v1 Announce Type: new Abstract: Confidential computing is becoming a practical deployment requirement for AI inference workloads that process sensitive inputs or protect proprietary mo→11 Aug 2026Who Verifies the Benchmark? Decentralizing Trust in Large Language Model EvaluationarXiv:2608.07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims tha→15 Sept 2026TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOpsarXiv:2609.14762v1 Announce Type: cross Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk→25 Sept 2026Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context InferencearXiv:2602.08329v2 Announce Type: replace-cross Abstract: A core bottleneck in large language model (LLM) inference is the cost of attending over the ever-growing key-value (KV) cache. Although near-o→28 Sept 2026Energy Efficiency of Locally Deployed LLMs: A Preliminary Quantitative GPU Power Benchmark on Consumer HardwarearXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t
CompanyxAI1 recent entries10 Jul 2026Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond ImitationarXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m
CompanyDeepSeek8 recent entries31 Jul 2026Safety-Gated Agentic Supervisory Control on a Coupled Distillation Benchmark: Regime Map, Auditable Gate, and Co-Design FindingsarXiv:2607.27849v1 Announce Type: cross Abstract: An open-weight LLM can write composition setpoints every five minutes. What a plant still needs is a hard check: named constraints, logged margins, an→11 Aug 2026Who Verifies the Benchmark? Decentralizing Trust in Large Language Model EvaluationarXiv:2608.07762v1 Announce Type: new Abstract: LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims tha→4 Sept 2026Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable RewardsarXiv:2609.03181v1 Announce Type: new Abstract: We present Jina-OCR-v1, an end-to-end document parsing model built to serve on low-budget GPUs. It combines the compressed-vision encoder and the 3B mix→10 Sept 2026RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context ServingarXiv:2609.07008v1 Announce Type: new Abstract: Multi-head latent attention (MLA) exposes many logical query heads through one packed latent KV stream. This representation is memory efficient, but it →10 Sept 2026Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM ServingarXiv:2609.06853v1 Announce Type: cross Abstract: Shared key--value (KV) cache reuse improves large language model (LLM) serving, but it can also create a timing side channel that reveals whether a pr→22 Sept 2026Balancing Reasoning and Hardware Constraints in RAG Pipelines for Ukrainian Multi-Domain Document UnderstandingarXiv:2609.22124v1 Announce Type: new Abstract: This paper describes the system submitted to the UNLP 2026 Shared Task on Multi-Domain Document Understanding. The challenge required extracting precise→23 Sept 2026RoofLang: Enabling AI-Driven Architecting of LLM Inference SystemsarXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based. →12 Oct 2026Taking Tokenization off the Host for Agentic LLM ServingarXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still
CompanyNVIDIA8 recent entries14 Oct 2026InstantViR: Real-Time Video Inverse Problem Solver with Distilled Diffusion PriorarXiv:2511.14208v3 Announce Type: replace Abstract: Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constrai→14 Oct 2026Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language ModelsarXiv:2610.15781v1 Announce Type: new Abstract: Training-free pruning removes weights from pretrained large language models to reduce their deployment cost. However, existing approaches typically cons→14 Oct 2026Force Sensor-Based Picking Pattern Analysis and Two-Jaw Gripper Design for Cherry Tomato Robotic Harvesting in GreenhousearXiv:2610.18160v1 Announce Type: new Abstract: Robotic harvesting of cherry tomatoes in greenhouses remains challenging due to dense fruit clusters, delicate skin, and the need for gentle yet effecti→14 Oct 2026Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Hardware-Validated Benchmarking Study of Forward-Only AlgorithmsarXiv:2511.01061v2 Announce Type: replace Abstract: Backpropagation (BP) powers modern deep learning, but it must hold every activation in memory until a global backward sweep consumes it, and that sw→14 Oct 2026Embodied Zero-Shot Task Planning via Hardware-Aware LLM-VLM Integration for Grounded Robotic ManipulationarXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded →14 Oct 2026CAST: Real-Time Motion Capture for Any Skeleton TopologyarXiv:2610.14856v1 Announce Type: new Abstract: This paper studies the problem of recovering motion from monocular video, even when the target skeleton topology differs from the subject observed in th→14 Oct 2026BARTER: Compact Dynamic Sparse Training with Standard Dense KernelsarXiv:2610.16147v1 Announce Type: new Abstract: Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensi→14 Oct 2026AUGUstus: Autonomous Driving VLA Model with Unified Generation and UnderstandingarXiv:2610.16985v1 Announce Type: new Abstract: Vision-language-action (VLA) models show strong potential for end-to-end autonomous driving by leveraging world knowledge and understanding to excel in