KV Cache Steering for Inducing Reasoning in Small Language Models
☆46Jul 24, 2025Updated 7 months ago
Alternatives and similar repositories for cache-steering
Users that are interested in cache-steering are comparing it to the libraries listed below
Sorting:
- [NAACL'25] "Revealing the Barriers of Language Agents in Planning"☆13Jun 22, 2025Updated 9 months ago
- ☆16Jun 10, 2025Updated 9 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆98Nov 17, 2024Updated last year
- ☆15Jan 12, 2026Updated 2 months ago
- ☆15Apr 11, 2024Updated last year
- Fork of Flame repo for training of some new stuff in development☆19Updated this week
- Resa: Transparent Reasoning Models via SAEs☆48Sep 23, 2025Updated 6 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 2 months ago
- Official Code for "Learning to Reason via Mixture-of-Thought for Logical Reasoning"☆28Nov 20, 2025Updated 4 months ago
- ☆12Apr 17, 2025Updated 11 months ago
- ☆13Jul 2, 2025Updated 8 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆29Jul 24, 2025Updated 7 months ago
- ☆15Mar 20, 2025Updated last year
- ☆15Feb 21, 2024Updated 2 years ago
- [ICML-2025] We introduce Lie group Relative position Encodings (LieRE) that goes beyond RoPE in supporting n-dimensional inputs.☆14Aug 8, 2025Updated 7 months ago
- A reinforcement learning environment for the IGLU 2022 at NeurIPS☆36May 27, 2023Updated 2 years ago
- ☆17Sep 1, 2024Updated last year
- Source code accompanying the NeurIPS 2022 paper "Learning Partial Equivariances From Data"☆10Nov 18, 2022Updated 3 years ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆20Jan 24, 2025Updated last year
- Training, optimization and deployment of Object Detection model with dinov2 backbone for efficient inference on NVIDIA Jetson☆13Jul 26, 2025Updated 7 months ago
- BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution☆58Oct 13, 2025Updated 5 months ago
- [ICML 2024] Sparse Model Inversion: Efficient Inversion of Vision Transformers with Less Hallucination☆14Apr 29, 2025Updated 10 months ago
- Generate Python docstrings automatically with LLM and syntax trees☆20Jun 13, 2025Updated 9 months ago
- ☆21Jul 21, 2025Updated 8 months ago
- CLI tool for submitting GPU kernels☆13May 26, 2025Updated 9 months ago
- Algorithms for approximate attention in LLMs☆21Apr 14, 2025Updated 11 months ago
- ☆24Apr 3, 2025Updated 11 months ago
- torchvision-based transforms that provide access to parameterization☆16Dec 4, 2025Updated 3 months ago
- Code for [Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models.☆13Nov 27, 2024Updated last year
- Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (M…☆31Nov 20, 2024Updated last year
- Differentiable Weightless Neural Networks☆34Feb 2, 2026Updated last month
- Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (ACL 2025, oral)☆32Jun 14, 2025Updated 9 months ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆55Updated this week
- Continuous regular group convolutions for Pytorch☆12Jun 9, 2024Updated last year
- [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models☆35Jun 12, 2024Updated last year
- [CVPR 2025 Highlight] FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation☆25Jun 16, 2025Updated 9 months ago
- Code for the MTEB Arena☆24Jul 2, 2025Updated 8 months ago
- Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision☆19Apr 1, 2025Updated 11 months ago
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆19Mar 10, 2025Updated last year