On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “Qwen3-8B”

Financial Text Classification Based On rLoRA Finetuning On Qwen3-8B modelcs.LG

Qwen3-8B outperforms classical models in financial text classification.

problem Financial text classification for trading systems and sentiment analysis.

method Noisy Embedding Instruction Finetuning and Rank-stabilized Low-Rank Adaptation.

result Qwen3-8B achieves better classification accuracy and fewer training epochs.

financial text classification Qwen3-8B Noisy Embedding instruction-following low-rank optimization

2025-11-29abs ↗pdf ↗

Single-stream Policy Optimizationcs.LG

SPO optimizes LLMs by eliminating group-based baselines and variance issues.

problem Frequent degenerate groups and synchronization barriers in group-based policy optimization methods.

method Single-stream Policy Optimization (SPO) replaces per-group baselines with a persistent, KL-adaptive value tracker and global advantage normalization.

result SPO converges more smoothly and attains higher accuracy than GRPO, improving maj@32 by +3.4 pp across five math benchmarks.

Large Language Models Policy Optimization Group-Based Methods Degenerate Groups Advantage Normalization

2025-09-16abs ↗pdf ↗

Instruction Finetuning LLaMA-3-8B Model Using LoRA for Financial Named Entity Recognitionq-fin.CP

Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.

problem LLMs struggle with financial NER, especially differentiating entities and amounts.

method Instruction fine-tuning combined with LoRA for parameter-efficient learning.

result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.

financial NER LLaMA-3-8B instruction fine-tuning LoRA state-of-the-art

2026-01-15abs ↗pdf ↗

OBLR-PO: A Theoretical Framework for Stable Reinforcement Learningstat.ML

Unified framework for stable RL learning with theoretical guarantees.

problem Lack of systematic theoretical principles guiding RL post-training methods.

method Unified theoretical framework for policy-gradient estimators and optimization algorithms.

result Establishes unbiasedness, variance expressions, and convergence guarantees.

reinforcement learning policy optimization gradient estimation stability learning rate

2025-11-28abs ↗pdf ↗

Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITsq-fin.ST

Study proposes a multi-agent system using LLMs for REIT trading, outperforming benchmarks.

problem Low-volatility Chinese REIT market, low risk-adjusted returns.

method Multi-agent framework with four types of agents, prediction model pathways, fine-tuning.

result Multi-agent strategies outperform buy-and-hold in terms of return, Sharpe ratio, and drawdown.

REITs Real Estate Investment Trusts Multi-Agent System Large Language Models Trading Strategies

2026-01-22abs ↗pdf ↗

AIS: Adaptive Importance Sampling for Quantized RLstat.ML

AIS corrects rollout-training mismatch in quantized RL, improving speed and stability.

problem Rollout-training mismatch in quantized RL causes bias and training collapse.

method Adaptive Importance Sampling (AIS) adjusts gradient correction per batch.

result AIS matches BF16 baseline on most tasks while improving speed.

Reinforcement Learning Quantized RL Importance Sampling Gradient Correction FP8

2026-05-13abs ↗pdf ↗

INFUSER: Influence-Guided Self-Evolution Improves Reasoningcs.LG

INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.

problem Improving reasoning in language models with minimal external supervision.

method INFUSER uses a Generator and Solver to co-evolve iteratively, rewarding the Generator with an influence score and the Solver with correctness rewards.

result INFUSER outperforms self-evolution baselines by over 20% on Olympiad and SuperGPQA benchmarks.

self-evolution language models reasoning influence score co-training

2026-06-08abs ↗pdf ↗

INFUSER: Influence-Guided Self-Evolution Improves Reasoningcs.LG

INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.

problem Improving reasoning through self-evolution

method INFUSER uses a generator and solver co-evolving in a document pool to improve reasoning.

result INFUSER outperforms strong self-evolution baselines on Olympiad and SuperGPQA benchmarks.

self-evolution reasoning co-training document pool instruction-finetuned

2026-06-08abs ↗pdf ↗

TREK: Distill to Explore, Reinforce to Refinecs.LG

TREK uses distillation to help students solve hard problems.

problem Stalled progress on hard prompts when current policy lacks useful reasoning trajectories.

method TREK combines distillation and reinforcement learning to expand student support.

result TREK significantly improves student performance on mathematical reasoning and agentic tasks.

policy optimization distillation reinforcement learning student support hard prompts

2026-07-06abs ↗pdf ↗