9 citations · 21 across the 22 of their papers we have counts for
23 papers
SteerSearch: Interactive Search Reasoning with Mid-Response Steering
Udit Thakur, Baohao Liao, Matteo Nulli +4
Search-augmented language models increasingly serve as long-horizon research agents, yet most open training methods assume a fixed user goal throughout search. We study mid-respons…
Multi-Turn On-Policy Distillation with Prefix Replay
Baohao Liao, Hanze Dong, Christof Monz +3
We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn…
LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
Linyang He, Qiyao Yu, Hanze Dong +5
Mathematical reasoning is a hallmark of human intelligence, and whether large language models (LLMs) can meaningfully perform it remains a central question in artificial intelligen…
Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao, Hanze Dong, Xinxing Xu +2
Group Relative Policy Optimization (GRPO) has recently emerged as a practical recipe for aligning large language models with verifiable objectives. However, under sparse terminal r…
Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives
Wei Xiong, Chenlu Ye, Baohao Liao +6
Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to u…
How Well Do Vision-Language Models Understand Movies?
Emmanouil Zaranis, António Farinhas, Saul Santos +28
Vision-language models (VLMs) can increasingly handle extended contexts and answer questions about long videos--but can they understand the narrative structure of movies as humans…
Lost at the Beginning of Reasoning
Baohao Liao, Xinyi Chen, Sara Rajaee +5
Recent advancements in large language models (LLMs) have significantly advanced complex reasoning capabilities, particularly through extended chain-of-thought (CoT) reasoning that…
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation
Stefan Vasilev, Christian Herold, Baohao Liao +3
This paper introduces Unilogit, a novel self-distillation method for machine unlearning in Large Language Models. Unilogit addresses the challenge of selectively forgetting specifi…
Fractured Chain-of-Thought Reasoning
Baohao Liao, Hanze Dong, Yuhui Xu +4
Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference…
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning
Baohao Liao, Christian Herold, Seyyed Hadi Hashemi +3
As large language models (LLMs) scale, model compression is crucial for edge deployment and accessibility. Weight-only quantization reduces model size but suffers from performance…
Reward-Guided Speculative Decoding for Efficient LLM Reasoning
Baohao Liao, Yuhui Xu, Hanze Dong +5
We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combine…
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
Baohao Liao, Christof Monz
Parameter-efficient finetuning (PEFT) methods effectively adapt large language models (LLMs) to diverse downstream tasks, reducing storage and GPU memory demands. Despite these adv…
IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation
Baohao Liao, Christian Herold, Shahram Khadivi +1
This paper introduces two multilingual systems, IKUN and IKUN-C, developed for the general machine translation task in WMT24. IKUN and IKUN-C represent an open system and a constra…
The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models
Xinyi Chen, Baohao Liao, Jirui Qi +4
Following multiple instructions is a crucial ability for large language models (LLMs). Evaluating this ability comes with significant challenges: (i) limited coherence between mult…
Is It a Free Lunch for Removing Outliers during Pretraining?
Baohao Liao, Christof Monz
With the growing size of large language models, the role of quantization becomes increasingly significant. However, outliers present in weights or activations notably influence the…
ApiQ: Finetuning of 2-Bit Quantized Large Language Model
Baohao Liao, Christian Herold, Shahram Khadivi +1
Memory-efficient finetuning of large language models (LLMs) has recently attracted huge attention with the increasing size of LLMs, primarily due to the constraints posed by GPU me…
ITEm: Unsupervised Image-Text Embedding Learning for eCommerce
Baohao Liao, Michael Kozielski, Sanjika Hewavitharana +3
Product embedding serves as a cornerstone for a wide range of applications in eCommerce. The product embedding learned from multiple modalities shows significant improvement over t…
Ask Language Model to Clean Your Noisy Translation Data
Quinten Bolding, Baohao Liao, Brandon James Denis +2
Transformer models have demonstrated remarkable performance in neural machine translation (NMT). However, their vulnerability to noisy input poses a significant challenge in practi…
Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning
Baohao Liao, Shaomu Tan, Christof Monz
Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sa…
Parameter-Efficient Fine-Tuning without Introducing New Latency
Baohao Liao, Yan Meng, Christof Monz
Parameter-efficient fine-tuning (PEFT) of pre-trained language models has recently demonstrated remarkable achievements, effectively matching the performance of full fine-tuning wh…
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token
Baohao Liao, David Thulke, Sanjika Hewavitharana +2
The pre-training of masked language models (MLMs) consumes massive computation to achieve good results on downstream NLP tasks, resulting in a large carbon footprint. In the vanill…
Towards prediction of turbulent flows at high Reynolds numbers using high performance computing data and deep learning
Mathis Bode, Michael Gauding, Jens Henrik Göbbert +3
In this paper, deep learning (DL) methods are evaluated in the context of turbulent flows. Various generative adversarial networks (GANs) are discussed with respect to their suitab…
Back-translation for Large-Scale Multilingual Machine Translation
Baohao Liao, Shahram Khadivi, Sanjika Hewavitharana
This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to bu…