SAGE: Training-Free Semantic Evidence Composition for Edge-Cloud Inference under Hard Uplink Budgets
SAGE method for edge-cloud inference selects semantic content beyond attention importance under hard uplink bit-budget constraints.
Search the full wire by company, model, lab, or keyword. Every story we have ever aggregated.
SAGE method for edge-cloud inference selects semantic content beyond attention importance under hard uplink bit-budget constraints.
Release of German free-association norms dataset for 5,877 cue words as part of multilingual Small World of Words project.
Benchmark comparison of Kimi K2.5 vs K2.6 on MineBench; K2.6 shows inconsistent but high-ceiling performance at $2.35 cost.
Kimi K2.6 vs K2.5 benchmark on MineBench shows cost-effective performance gains at $2.35 total.
Latitude's new AI-native platform, Voyage, aims to help gamers create their very own role-playing game.
User reports Image Gen 2 demonstrates advanced reasoning in color composition, generating cinematic palettes and tonal coherence across panels.
AblateCell agent reproduces baselines and systematically ablates components in AI virtual cell repositories for biological research.
Simon Willison comments on synthetic data injection into training sets via absurdist example (pelicans on bicycles).
Comparative study of output consistency across GPT-4.1, Claude Sonnet 4.6, Gemini 2.5 Flash for exercise prescriptions with safety analysis.
Romanian legal domain GEC dataset addresses grammatical error correction in low-resource language niche; narrow domain applicability.
Theoretical reduction from online learning to multicalibration via EVI solvers; advances in regret minimization analysis.
User documents that Gemma 4's default vision budget (280 tokens) is too low; Variable Image Resolution mode requires manual tuning.
Corpus of Sardinian extemporaneous poetry for NLP; minority language resource with limited frontier AI relevance.
Empirical study: LLMs measurably alter peer review opinions on clarity, originality at top AI conferences.
Framework for long-horizon terminal agents using observational context compression; reduces quadratic token cost via self-evolving compression.
Bond wants you to get off the couch and get back into the real world, its creator says. The new platform's AI system is designed to motivate users to do things away from the app.
Lyapunov stability analysis of constant-stepsize Q-learning via switched systems; theoretical convergence bounds.
RL post-training for visual semantic arithmetic in multimodal LLMs; extends relational reasoning from text to images.
Interpretability method for ColBERT retrieval via learned latent space reference; targets biomedical/clinical ranking diagnostics.
Inference-time hallucination detection in SpeechLLMs via attention metrics (AUDIORATIO, AUDIOCONSISTENCY); avoids gold-standard requirement.
EgoSelf system: graph-based interaction memory for personalized egocentric assistants; addresses long-term user context integration.
SE(3)-equivariant transformer with contrastive learning for protein-ligand structure encoding in drug discovery.
Membership inference attacks benchmark against SOTA LLMs to detect training data contamination via black-box methods.
Theoretical framework decoupling geometry from probability assumptions in classical generalization analysis.
LSTM and attention-based models for heat stress prediction in construction workers using wearable sensor data.
User reports Claude Opus 4.7 performs worse than 4.6 on file search and factual accuracy tasks.
Multi-agent LLM framework addresses actor-observer cognitive bias via dialectical alignment in self-reflection loops.
Graph-based semantic decoupling for emotion-cause pair extraction in dialogue conversations.
Debiased preference curation and iterative training for multimodal reward models aligning MLLMs with human preferences.
YouTube is expanding its AI likeness detection tool to celebrities, giving talent and their reps a way to find and remove deepfakes.