L-layer transformers under Log-ICoT curriculum provably learn k-parity with poly(n) samples and log k stages, matching explicit CoT efficiency without inference overhead.
hub Mixed citations
arXiv preprint arXiv:2311.01460 , year=
Mixed citation behavior. Most common role is background (60%).
24
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 3
baseline 1
dataset 1
citation-polarity summary
representative citing papers
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
RiM trains LLMs to perform latent reasoning via fixed memory blocks processed in one forward pass using a two-stage curriculum, matching or exceeding prior latent methods on benchmarks.
COLAGUARD matches explicit-reasoning guardrail performance on safety benchmarks while delivering 12.9X speedup and 22.4X token reduction by propagating hidden states instead of generating text.
A synthetic pipeline creates and internalizes reasoning traces in VLMs for long-context visual document understanding, with a 32B model surpassing a 235B model on MMLongBenchDoc and showing 12.4x fewer output tokens.
SpiralThinker stabilizes iterative latent reasoning in LLMs via text-latent interleaving and progressive alignment, achieving SOTA results among latent baselines on math, logic, and commonsense tasks.
CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.
Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency trade-offs.
Coarser compressed CoT needs more SFT data, scales differently with repetition, and RL later breaks apart the compressed steps learned in SFT.
TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
Two-stage fine-tuning distills multi-agent debate into single LLMs, matching performance at 93% lower token cost while revealing agent-specific activation subspaces for steering.
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
CCoT generates variable-length continuous contemplation tokens that compress explicit reasoning chains, enabling additional dense reasoning and accuracy gains in off-the-shelf language models while allowing adaptive control of token count.
Frontier AI models' no-CoT 50% task-completion time horizons have doubled yearly over six years, reaching over 3 minutes for GPT-5.5 with projections to 25 minutes by 2030.
GPlan compresses LLM reasoning into small models via Progressive Implicit CoT Distillation and Spatiotemporal Counterfactual DPO to generate logically coherent and physically executable intent sequences for recommendation.
Injecting noise into LLM latent trajectories creates diverse reasoning paths whose agreement acts as a confidence signal for selective abstention, cutting error rates from 40-70% to under 15% on math tasks.
MarCos modifies transformers to perform continuous multi-step reasoning by mapping thought-level continuous states directly to next-thought distributions, achieving substantial wall-clock speedups on math problems.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
Transformers Provably Learn to Internalize Chain-of-Thought
L-layer transformers under Log-ICoT curriculum provably learn k-parity with poly(n) samples and log k stages, matching explicit CoT efficiency without inference overhead.
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
Unlocking the Working Memory of Large Language Models for Latent Reasoning
RiM trains LLMs to perform latent reasoning via fixed memory blocks processed in one forward pass using a two-stage curriculum, matching or exceeding prior latent methods on benchmarks.
-
Robust and Efficient Guardrails with Latent Reasoning
COLAGUARD matches explicit-reasoning guardrail performance on safety benchmarks while delivering 12.9X speedup and 22.4X token reduction by propagating hidden states instead of generating text.
-
Internalized Reasoning for Long-Context Visual Document Understanding
A synthetic pipeline creates and internalizes reasoning traces in VLMs for long-context visual document understanding, with a 32B model surpassing a 235B model on MMLongBenchDoc and showing 12.4x fewer output tokens.
-
SpiralThinker: Latent Reasoning through an Iterative Process with Text-Latent Interleaving
SpiralThinker stabilizes iterative latent reasoning in LLMs via text-latent interleaving and progressive alignment, achieving SOTA results among latent baselines on math, logic, and commonsense tasks.
-
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.
-
Training Large Language Models to Reason in a Continuous Latent Space
Coconut lets LLMs perform reasoning directly in continuous latent space by recycling hidden states as inputs, outperforming standard chain-of-thought on search-intensive logical tasks with better accuracy-efficiency trade-offs.
-
Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training
Coarser compressed CoT needs more SFT data, scales differently with repetition, and RL later breaks apart the compressed steps learned in SFT.
-
TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens
TTE-Flash trains latent think tokens with CoT generation loss and embedding tokens with contrastive loss to deliver high-performance multimodal representations without generating explicit reasoning at inference time.
-
Factorized Latent Reasoning for LLM-based Recommendation
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
-
Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
Two-stage fine-tuning distills multi-agent debate into single LLMs, matching performance at 93% lower token cost while revealing agent-specific activation subspaces for steering.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
SeLaR: Selective Latent Reasoning in Large Language Models
SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.
-
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent Planning
LLMs discover latent planning strategies up to five steps during training and execute them up to eight steps at test time, with larger models reaching seven under few-shot prompting, revealing a dissociation between discovery and execution.
-
LightThinker++: From Reasoning Compression to Memory Management
LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.
-
LIMO: Less is More for Reasoning
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
-
Compressed Chain of Thought: Efficient Reasoning Through Dense Representations
CCoT generates variable-length continuous contemplation tokens that compress explicit reasoning chains, enabling additional dense reasoning and accuracy gains in off-the-shelf language models while allowing adaptive control of token count.
-
Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models
Frontier AI models' no-CoT 50% task-completion time horizons have doubled yearly over six years, reaching over 3 minutes for GPT-5.5 with projections to 25 minutes by 2030.
-
Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap
GPlan compresses LLM reasoning into small models via Progressive Implicit CoT Distillation and Spatiotemporal Counterfactual DPO to generate logically coherent and physically executable intent sequences for recommendation.
-
NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning
Injecting noise into LLM latent trajectories creates diverse reasoning paths whose agreement acts as a confidence signal for selective abstention, cutting error rates from 40-70% to under 15% on math tasks.
-
Deep Thinking by Markov Chain of Continuous Thoughts
MarCos modifies transformers to perform continuous multi-step reasoning by mapping thought-level continuous states directly to next-thought distributions, achieving substantial wall-clock speedups on math problems.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
- Can Aha Moments Be Fake? Towards Quantifying Decorative and True Thinking in Chain-of-Thought