arXiv AI
Jun 15
Token-Level LLM Collaboration via FusionRoute
arXiv:2601. 05106v5 Announce Type: replace Abstract: Large language models (LLMs) exhibit strengths across diverse domains.
FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding
arXiv:2608. 06819v1 Announce Type: cross Abstract: Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge.
Related stories
arXiv Machine Learning
Sep 22
Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Efficient Instruction Tuning
The paper introduces BRIDGE, a method for efficient instruction tuning of large language models that jointly selects prompt context and response supervision. BRIDGE uses a shared validation-directed interaction surrogate to evaluate token utility conditioned on the other side’s retained state, and employs budgeted alternating selection and structure-aware projection to produce coherent supervision spans. Experiments across three model families show BRIDGE outperforms independent selection methods in mathematical reasoning, code generation, and instruction following, with its advantage increasing as compression grows.
arXiv AI
Jun 15
SuperThoughts: Reasoning Tokens in Superposition
arXiv:2606. 13862v1 Announce Type: cross Abstract: Long Chain-of-Thought (CoT) reasoning improves LLM problem-solving but is computationally expensive due to sequential token generation.
arXiv Computation and Language
3d ago
DEdit: Iterative Draft Editing for Speculative Decoding
arXiv:2609.38510v1 Announce Type: new Abstract: Speculative decoding accelerates autoregressive LLMs by having a lightweight drafter propose tokens that the target model verifies in parallel. Diffusi...
arXiv AI
Jun 2
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
arXiv:2606. 01682v1 Announce Type: cross Abstract: Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths.
arXiv AI
2d ago
Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads
arXiv:2610.00888v1 Announce Type: cross Abstract: Multi-token prediction (MTP) improves the throughput of autoregressive generation by enabling the language model to draft multiple next tokens per fo...
arXiv AI
Jun 16
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
arXiv:2511. 08577v3 Announce Type: replace-cross Abstract: Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications.
arXiv Machine Learning
Jul 3
PARTREP: Learning What to Repeat for Decoder-only LLMs
arXiv:2607. 01792v1 Announce Type: cross Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones.
Hugging Face Trending Papers
Jun 1
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels.
arXiv AI
Aug 7
DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
arXiv:2608. 06243v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models using automatically verifiable outcome signals, but these signals are typically sparse and at the sequence-level.
arXiv AI
Sep 1
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
arXiv:2608.30632v1 Announce Type: cross Abstract: Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language...
arXiv AI
Jul 15
Rethinking Reward Models for Multi-Domain Test-Time Scaling
arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.