$TOKN token

Latest papers

1. Representation Conditioning for Generation cs.CV · 14 Oct · 2 hits

   …(RECON), to improve semantics in later layers. During training, we feed the pretrained vision encoder tokens into later layers; during inference, because we no longer have the clean image, we reuse the MLP head…

2. VITAL: From Visual Motion to Precise Action cs.CV · 14 Oct · 1 hit

   …the dominant maneuver but leaves centimeter-scale errors. We therefore introduce VITAL (Vision-Induced Tokens for Action Learning), an action tokenizer that couples a visually derived motion scaffold with a…

3. Continuum Attention cs.LG · 14 Oct · 1 hit

   …interpolated values yields exact normalized attention from closed form exponential moments, including half token boundary contributions. The gradients follow analytically from moments of order at most two, enabling…

4. Recovering Reliable Supervision via Critique-Guided On-Policy Distillation cs.LG · 14 Oct · 1 hit

   On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix…

5. Reliability-Aware Multimodal Sentiment Prediction Under Local Modality Missingness cs.CV · 14 Oct · 2 hits

   …network (RM-Net) keeps the original temporal positions, represents unobserved positions with a learned token, outputs bounded per-modality intensity contributions gated by observation quality, and is trained with…

6. ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps cs.AI · 14 Oct · 1 hit

   …reaches task score 0.842, grounding F1 0.816, evidence recall 0.873, 1.74 accepted calls, 286.5K visual tokens, and 742ms p95 latency. Dense replay of issued certificates shows 0.992 action agreement and a 0.988…

7. VASPO: Self-Distillation with Privileged Value Estimation cs.CL · 14 Oct · 2 hits

   …supervision for reasoning models via a privileged self-teacher. However, this supervision reflects local token preferences rather than the expected return of an unguided student continuation. Recent methods combine…

8. A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records cs.LG · 14 Oct · 1 hit

   …analysis did not support a monotonic relation between score and forecasting benefit after endpoint and token-count adjustment (1.96 days per SD; 95% CI, -0.75 to 4.68). In the frozen catalog-q90 high-semantic…