… The benchmark thus jointly evaluates symbolic causal reasoning , data science, uncertainty quantification , abstention, and tool use / coding . View arXiv page View PDF GitHub 1 Add to collection Community We introduce CausalDS , a benchmark generator for agentic causal data science. …
… The following papers were recommended by the Semantic Scholar API QuIVer: Rethinking ANN Graph Topology via Training-Free Binary Quantization 2026 QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling 2026 OCTOPUS: Optimized KV Cache for Transforme… …
… The following papers were recommended by the Semantic Scholar API DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers 2026 Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V 2026 OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization 2026 Ta… …
… GBC models a multi-agent system as a computational graph and uses gradient-based signals to quantify how each agent output influences downstream agents at the token level. …
… The following papers were recommended by the Semantic Scholar API Quantum-enhanced Large Language Models on Quantum Hardware via Cayley Unitary Adapters 2026 Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis 2026 Structure-Aware Transformers for Learning Near-Optimal Trotter… …
… 2026 ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports 2026 Bug Report Specification Refinement with Trajectory Guidance for Automated Program Repair 2026 Understanding Agent-Based Patching of Compiler Missed Optimizations 2026 ChainSWE: Benchmar… …
… The following papers were recommended by the Semantic Scholar API Simulating quantum circuits with a neural statebank 2026 Basis-Adaptive Sparse-State Simulation of Quantum Circuits 2026 Not Your Usual FFT: QFT$\rightarrow$FFT via Classical Quantum-Circuit Simulation 2026 Efficiently simulable quan… …
… KV-cache quantization can help improve this, but current methods are evaluated under prefill-like settings and errors behave differently under autoregressive decoding . We show that in the latter regime, quantization errors accumulate across timesteps, driven primarily by incorrect token scales . …
… The following papers were recommended by the Semantic Scholar API DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression 2026 Variable Bit-width Quantization: Learning Per-Group Precision for"Bigger-but-Smaller"Language Models 2026 BiSCo-LLM: Lookup-F… …
… Key findings from our deployment on one of the largest clinical FHIR repositories in Europe ~2B resources, 1.7M patients : Across 7,326 clinician judgments in a retrospective lymphoma registry study, physicians accepted 96.5% of extractions, with per-type acceptance ranging from 80% to 99% We quant… …