Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
Systematic study of DPO hyperparameter landscape across model scales reveals optimal learning rate and β-regularization shift with size; direct transfer between scales unreliable.
Benchmark study of associative creativity in MLLMs vs. humans on abstract visual stimuli with controlled naming difficulty; evaluates originality and effectiveness.
PhyNet framework for industrial fault diagnosis treats physical variables as global constraints and response signals as diagnostic evidence in heterogeneous sensor streams.
Harness optimization for LM agents distinguishes elicitation (leveraging existing capabilities) from expansion (broadening solvable tasks) without weight updates; implications for recursive self-improvement.
Differentiable graph-based implicit solver for PDEs on unstructured grids with forward and inverse problem capability, treating stiff equations as constraints.
Generative AI models run on powerful chips known as GPUs, which depend on stacks of specialized memory chips packaged with the processor. To meet growing demand for memory, Samsung is building a massive new semiconductor manufacturing complex in Pyeongtaek, South Korea. Three fabs already operate around the clock, and a fourth is coming online. Construction…
Verification-guided training for neural Hamilton-Jacobi safety certificates uses probabilistic enumeration to detect forward-invariance violations and generate targeted counterexamples.
LLMs hallucinate in cross-language code translation via semantic conflicts, target-language violations, and inconsistent dependencies; existing mitigations insufficient.
VISH framework selects compact hotword subsets for speech-LLM contextual ASR via frame-level CTC posterior verification; training-free and scalable via shared-prefix Viterbi search.
Token-level framework detects and localizes AI-generated code within files using multi-granularity analysis, outperforming file-level compression methods.
Vision-language model matches acoustic patterns to cavitation states in industrial pipelines using operating-condition-aware semantic descriptions.
UvA-MT uses LLM sampling, refinement, and pairwise voting for WMT26 machine translation across 23 language pairs without task-specific training.
LaLa-World demonstrates JEPA-style latent world models learning across simulation, robotics, and video using language-conditioned actions for planning.
SAPD learns LLM agent policies from offline trajectories without environment interaction, combining offline RL with policy refinement to avoid forgetting.
SciDiagBench provides type-specific evaluation of AI-generated scientific diagrams, aligning VLM assessment with human peer-review criteria.
Novel optimizer for online continual learning balances plasticity and stability via Polyak-Ruppert and Primal averaging against catastrophic forgetting.
COMPASS agentic router selects optimal LLMs by profiling capabilities via tools and pairwise selection, achieving 69.85% accuracy at lower cost than trained baselines.
SMART maps ASR errors to semantic segments and applies contextual rubrics to evaluate meaning-altering transcription errors beyond word error rate.
Privacy-preserving inference embeds user prompts locally via 55.6M-param transform before passing to frozen Qwen 27B, preventing host access to plaintext.
RAG-NIMBF benchmarks RAG pipeline configurations via non-invasive ablation to guide chunking, embedding, retrieval, and generation model choices.
ProVe reverses speculative decoding: large model proposes token blocks, smaller model verifies in parallel, improving LLM inference speed.
LatBridge enables safe model replacement in multi-agent systems by bridging latent-communication interfaces across heterogeneous agent architectures.
SliMOO applies multi-objective evolutionary search to LLM depth pruning, preserving task-diverse capabilities while reducing memory and latency.
Neural decoder for error-correcting codes using discrete diffusion with certified optimality via LP relaxation and beam search.
Agentic workflow guides LLM coding agents to implement 6G physical-layer algorithms on embedded baseband silicon with vector assembly optimization.
TerraNostra-Bench evaluates land-use reconstruction at 1-km resolution via semantic segmentation, separating spatial downscaling from temporal rollout.
Mechanistic interpretability study investigates circuit overlap between linguistic and arithmetic capabilities in LLMs using causal analysis.
Theoretical framework connects scaling laws to geometric approximation, spectral analysis, and constrained optimization for resource allocation.
SLM-SS applies speech language models to multi-talker separation via token-based generation, optimizing for intelligibility over waveform metrics.
Relay uses LLM agents to diagnose and reuse repairs for historical software build failures, recovering 69.7% of failing OSS-Fuzz cases.