Paper page - FeatCal: Feature Calibration for Post-Merging Models
…Get this paper in your agent: hf papers read 2605.13030 Don't have the latest CLI? curl -LsSf https://hf.co/cli/install.sh | bash No dataset linking this paper Cite…
Search
Paper page - Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
…View arXiv page View PDF Add to collection Community https://x.com/MFarajtabar/status/2054275640946458785 Get this paper in your agent: hf papers read 2605.10889 Don't have the latest CLI…
Paper page - Triplet-Block Diffusion RWKV
…AI-generated summary Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and discrete diffusion models each address these weaknesses…
Paper page - Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
…Listed API prices vary by over an order of magnitude across providers, but we use price dispersion only as directional motivation, not as causal evidence of marginal cost. The core physical question…
Paper page - FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
…AI-generated summary Adapting pretrained models typically involves a trade-off between the high training costs of backpropagation and the heavy inference overhead of memory-based or in-context learning . We propose…
Paper page - DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
…Encoding cost stays roughly constant in K instead of scaling with it. Findings. Multi-token helps every diffusion backbone we test, on every benchmark (MS MARCO, TREC DL'19/'20, BEIR-7…
Paper page - Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States
…We introduce Policy Optimization with Internal State Value Estimation ), which obtains a baseline at negligible cost by using the policy model's internal signals already computed during the policy forward pass. A…
Paper page - MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
…AI-generated summary Mixture-of-Experts (MoE) architectures in Large Language Models (LLMs) have significantly reduced inference costs through sparse activation . However, this sparse activation paradigm also introduces new safety challenges. Since…
Paper page - Teaching Language Models to Think in Code
…Improving the Performance of Non-Thinking Models at No Cost (2026) Balanced Thinking: Improving Chain of Thought Training in Vision Language Models (2026) Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence…
Paper page - Fast Byte Latent Transformer
…All methods may achieve an estimated memory-bandwidth cost over 50% lower than BLT on generation tasks. Each approach offers its own unique advantages, together removing key barriers to the practical use…