SourceMar 14, 20262026-03-144 minVerified
When Harmless Tasks Process Harmful User Content
Examines how LLMs should handle harmful user-provided text in harmless tasks like summarization, translation, and classification.
SourceMar 13, 20262026-03-134 minVerified
ARROW Reframes Memory Efficient Continual Reinforcement Learning
ARROW extends DreamerV3 with dual buffers and distribution-matching replay to reduce forgetting under memory limits.
SourceMar 13, 20262026-03-134 minVerified
Evaluating LLM-Based Mandarin-to-English Translation with Automated Metrics
Examines how far automated evaluation can match human judgment in Mandarin-to-English LLM translation and where bias may distort results.
SourceMar 13, 20262026-03-135 minVerified
Single RGB-D Hand Retargeting for Robot Teleoperation
A low-cost teleoperation approach using a single RGB-D camera for hand tracking, 3D reconstruction, and robot retargeting.
SourceMar 13, 20262026-03-135 minVerified
Stable Spike for Low-Latency SNN Consistency Optimization
A concise look at Stable Spike, dual consistency optimization, and bitwise AND for more stable low-latency SNN inference.
SourceMar 13, 20262026-03-134 minVerified
STAIRS-Former for Variable-Agent Offline Multi-Task MARL Generalization
A transformer-based offline multi-task MARL approach targeting variable agent counts and generalization to unseen scenarios.
CommunityMar 13, 20262026-03-134 minVerified
Turning AI Ideas Into University Patent Strategy
A practical guide to turning AI ideas into patents through university invention rules, prototype planning, and claim-ready differentiation.
SourceMar 13, 20262026-03-134 minVerified
UAV-MARL Reframes Medical Drone Delivery as Collaborative Decisions
A look at UAV-MARL, which treats medical drone delivery as multi-agent collaborative decision-making, not just routing.
CommunityMar 12, 20262026-03-125 minVerified
Cash vs Unlimited AI Access: ROI Decision Framework
Compare monthly cash vs future unlimited generative AI using ROI, including review, security, and policy-compliance costs.
SourceMar 12, 20262026-03-124 minVerified
Measuring LLM Gaps With LatAm Context QA Benchmarks
A LatAm-focused QA set (26k+) links Wikidata and Wikipedia to measure LLM gaps by country and cultural context.
CommunityMar 12, 20262026-03-124 minVerified
Rethinking Research Automation Forecasts Beyond Speed And Accuracy Metrics
Don’t equate tokens/sec or speedups with research automation; fix success, time budget, retries, and verification to forecast.
SourceMar 11, 20262026-03-114 minVerified
LLM Orchestrates Superconducting Qubit Control And Measurement Experiments
Overview of an LLM framework that automates superconducting qubit control and measurement via schema-less tool generation, plus safety and logging needs.
SourceMar 11, 20262026-03-114 minVerified
Measure Generative Search Visibility as Distributions, Not KPIs
Because citations can be non-deterministic, treat visibility as a sampled distribution and compare it statistically over time.
SourceMar 11, 20262026-03-114 minVerified
Private Dataset Condensation for Classical Clinical Models
arXiv:2603.09356 discusses dataset condensation for medical data, extending to trees and Cox via DP and zero-order optimization.
SourceMar 11, 20262026-03-115 minVerified
Verifier Rewards With Executable Checkers For Multi-Turn Agents
Using executable per-instance checkers to provide verifiable rewards for multi-turn tool agents, reducing labeling while surfacing risks.
CommunityMar 11, 20262026-03-115 minVerified
When Prompts Shrink, Video Creation Becomes Pipeline Operations
As prompts shrink, video work shifts from generating to operating: lock identity with references, storyboard panel prompts, set multimodal priority rules, and track rights risk.
SourceMar 10, 20262026-03-104 minVerified
ABRA Learns Batch-Invariant Representations for Cell Painting Screens
ABRA applies adversarial learning to reduce batch effects in cell painting, balancing batch invariance with fine-grained class discriminability.
SourceMar 10, 20262026-03-104 minVerified
Consensus Sampling Fails Without Verifiers For LLM Truthfulness
Without external verifiers, polling/majority-vote consensus over many samples can miss truth, even at 25× inference cost, and reinforce shared misconceptions.
SourceMar 10, 20262026-03-104 minVerified
Using LIM Energy Lower Bounds in System Design
Discusses whether LIM learning-energy lower bounds should be design KPIs or only benchmarks, given ADC/DAC and calibration overheads.
SourceMar 9, 20262026-03-094 minVerified
Disentangling Tokenizer Bias From Backbone Capability In Forecasting
Separate time-series gains from LLM backbone ability versus tokenizer/decoder bias using controlled swaps and LLM-free baselines.
SourceMar 9, 20262026-03-094 minVerified
Dynamic Chunking for Efficient Diffusion Transformer Inference
Overview of dynamic chunking for Diffusion Transformers, adapting compute by timestep and spatial detail to improve the cost-quality tradeoff.
SourceMar 9, 20262026-03-094 minVerified
Treat Label Disagreement As A Product Requirement
Review across seven venues (2020–2025) argues consensus labeling can erase sociotechnical signals; proposes rules for distribution labels.
CommunityMar 9, 20262026-03-094 minVerified
When Long-Term Memory Hurts New Task Learning
Long-term memory can boost performance yet cause negative forward transfer as tasks evolve. Design deletion, summarization, and replacement policies.
SourceMar 8, 20262026-03-084 minVerified
Adult Mode Requires Age Assurance And Safety Architecture
Adult mode is not a toggle: it combines age estimation, age verification, youth safeguards, policy enforcement, and risk-based gating.