arXiv AI June 4, 2026 By Zehua Cheng, Wei Dai, Jiahao Sun

Invariant Gradient Alignment for Robust Reasoning Distillation

arXiv:2606. 05025v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from shortcut learning: they systematically fail on out-of-distribution (OOD) inputs whose semantic surface differs from training data, even when the logical structure is identical.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 1

MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation

arXiv:2608.29623v1 Announce Type: cross Abstract: Recent advances in large reasoning models (LRMs) have shown strong performance on complex problems through long chain-of-thought (Long CoT) reasoning...

By Yangsong Lan, Renkai Hu, HongKai Zheng, Bo Zhang, Renzhi Wang, Hongliang Dai, Piji Li

efficiency benchmarks safety

arXiv Machine Learning

Sep 22

Do Student LLMs Inherit OOD Robustness? Invariance-Weighted Distillation for Reliable Knowledge Transfer

arXiv:2609.22566v1 Announce Type: cross Abstract: Knowledge distillation (KD) aims to compress high-performance teacher LLMs into lightweight students. However, distilled students often exhibit subst...

By Dileesha Kannangara, Sanghamitra Dutta

llms nlp efficiency benchmarks

arXiv AI

Aug 11

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

arXiv:2605. 15532v3 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets.

By Jaehun Jung, Hyunwoo Kim, Brandon Cui, Ximing Lu, David Acuna, Prithviraj Ammanabrolu, Yejin Choi

llms fine-tuning efficiency multimodal benchmarks

arXiv Machine Learning

Jul 14

Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation

arXiv:2607. 10805v1 Announce Type: cross Abstract: On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs).

By Keqin Peng, Chen Li, Yuanxin Ouyang, Yancheng Yuan, Liang Ding

llms efficiency benchmarks

arXiv AI

Jul 20

RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization

arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.

By Qiming Bao, Juho Leinonen, Paul Denny, Michael J. Witbrock

llms reinforcement-learning fine-tuning safety

arXiv Computer Vision

Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

MI-Distillation: Selecting from Model-Interpolated Instruct-Reasoning Data Spectrum for Chain-of-Thought Distillation

Do Student LLMs Inherit OOD Robustness? Invariance-Weighted Distillation for Reliable Knowledge Transfer

DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation

Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation

RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs