Tracked topic
…First, monocular SAM3D-style object reconstruction can hallucinate pose and unseen geometry, while manipulation benefits from stable object shape when calibrated multi-view observations are available. Second, the original KnowledgeBank mainly retrieves…
…Using a human-calibrated LLM judge framework , we show that prior diversity measures are unreliable proxies for approach-level diversity , and this mismatch carries over to diversity-aware RLVR , where target metrics…
…Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration (2026) Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing (2026) TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative…
…conditions and coordinate frames, EMMA performs joint inference of explicit parameters, implicit dynamical components, and calibration invariants within a unified continuous-time model . EMMA leverages a Liquid Time-Constant (LTC) network to…
…similar to this paper. The following papers were recommended by the Semantic Scholar API VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action Models (2026) Rewind-IL: Online Failure Detection and State…
…it solves it." 100 tasks across 15 domains, built on the TICOS framework (Task / Introspection / Calibration / Output / Self-correction) Already #5 globally on HF Datasets popularity Officially endorsed by the HF Evaluation…
…A Beta-Bernoulli Calibrator for LLM Forecasting (2026) Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation (2026) World Models Meet Language Models: On the Complementarity of Concrete and Abstract…
…Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting (2026) Hybrid Policy Distillation for LLMs (2026) Please give a thumbs up to this comment if you found it helpful! If…
…Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting (2026) Self-Supervised On-Policy Distillation for Reasoning Language Models (2026) LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language…
…and (2) a dual-objective reinforcement learning stage that independently refines CoT reasoning quality and calibrates the final reward, ensuring that higher-quality reasoning directly translates to superior model performance. View arXiv…