academic-paper

Tag

Cards List
#academic-paper

@yoheinakajima: my first SSRN paper :) https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7147798…

X AI KOLs Following · 2d ago

Yohei Nakajima announces his first SSRN paper, sharing a link to it.

0 favorites 0 likes
#academic-paper

From Patterns to Maze Structures: SMT-Based Path Synthesis and 2D/3D Construction

arXiv cs.AI · 2026-07-14 Cached

Introduces an SMT-based pipeline for synthesizing maze solution paths from input patterns and constructing planar and 3D maze structures. Extends a conference paper with detailed construction methods and SMT-LIB examples.

0 favorites 0 likes
#academic-paper

The Economics of Recursive Self-Improvement [pdf]

Hacker News Top · 2026-07-14 Cached

This paper examines the economic incentives and dynamics of recursive self-improvement in AI systems, addressing how such processes could scale and their implications for governance and safety.

0 favorites 0 likes
#academic-paper

BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving

arXiv cs.LG · 2026-07-13 Cached

BlockServe introduces block-grained continuous batching to address convergence heterogeneity in diffusion LLMs, enabling 1.9–10.6x throughput improvement over Fast-dLLM while maintaining generation quality.

0 favorites 0 likes
#academic-paper

COALA: Robust Contextualized Speech-augmented Language Modeling for ASR via Contrastive Regularizer and Biasing Score Estimation

arXiv cs.CL · 2026-07-10 Cached

COALA is a robust framework for contextual biasing in automatic speech recognition (ASR) that uses a contrastive regularizer and biasing score estimation to improve recognition of domain-specific entities from large biasing lists. Experiments on LibriSpeech show consistent superior performance.

0 favorites 0 likes
#academic-paper

SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation

arXiv cs.CL · 2026-07-08 Cached

SpanUQ introduces a lightweight probe for span-level uncertainty quantification in LLMs, using a DETR-style decoder and mixture of Beta distributions, achieving superior error localization and faster inference than sampling-based methods.

0 favorites 0 likes
#academic-paper

@QingQ77: Automatically convert academic paper PDFs into slides, posters, project homepages, Xiaohongshu notes, or WeChat public account articles https://github.com/QuZhan51496/paper2anything… A Claude Code skill pack that, given a paper PDF, can…

X AI KOLs Timeline · 2026-07-03 Cached

paper2anything is a Claude Code skill pack developed by Zhejiang University AI4GC Lab that automatically converts academic paper PDFs into slides, posters, project homepages, Xiaohongshu notes, or WeChat public account articles.

1 favorites 1 likes
#academic-paper

Evaluation Pitfalls and Challenges in Multimedia Event Extraction

arXiv cs.CL · 2026-06-26 Cached

This paper presents a systematic analysis of evaluation pitfalls in multimedia event extraction, identifying issues such as inconsistent data processing, inconsistent task assumptions, and overly relaxed evaluation settings that can lead to overestimated performance.

0 favorites 0 likes
#academic-paper

@raydistributed: RollArt is an impressive example of disaggregation in large-scale RL. https://cse.ust.hk/~weiwa/papers/rollart-osdi26.p…

X AI KOLs Following · 2026-06-20 Cached

RollArt presents a disaggregated architecture for large-scale reinforcement learning, demonstrating significant improvements in efficiency and scalability.

0 favorites 0 likes
#academic-paper

Synthetic Resonance: A Framework for Growth-Oriented Human-AI Relationships

arXiv cs.AI · 2026-06-18 Cached

This paper introduces 'synthetic resonance,' a framework for understanding meaningful human-AI relationships without attributing subjective experience to AI, and calls for further research.

0 favorites 0 likes
#academic-paper

TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table Reasoning

arXiv cs.CL · 2026-06-10 Cached

TabClaw is an open-source interactive AI agent for spreadsheet manipulation and table reasoning that uses LLMs to automate data analysis, support multi-table reasoning, and adapt to user preferences through memory and skill extraction.

0 favorites 0 likes
#academic-paper

FLaG: Fine-Grained Latent Grouping for Hallucination Detection

arXiv cs.LG · 2026-06-02 Cached

FLaG is a lightweight framework for hallucination detection in LLMs that models correctness via latent evidence groups and energy-based routing, achieving SOTA performance across benchmarks.

0 favorites 0 likes
#academic-paper

The Critical State of Cyberspacs

Lobsters Hottest · 2026-05-30 Cached

This academic paper addresses the current critical state of cyberspace, likely discussing vulnerabilities, threats, and governance challenges.

0 favorites 0 likes
#academic-paper

Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines

arXiv cs.CL · 2026-05-27 Cached

This survey reframes the alignment tuning of large language models as a data pipeline design problem, decomposing it into three stages: response synthesis, preference evaluation, and preference instantiation. It identifies design trade-offs and failure modes, and outlines open challenges such as prompt-level alignment and agentic settings.

0 favorites 0 likes
#academic-paper

@sheriyuo: Actually, I have been writing papers purely with AI from the very beginning. Previously I used DeepSeek R1, now I use V4. Since I don't have English academic writing ability, but I can tell by eye whether a sentence or passage is appropriate. As for Chinese writing, I am fairly confident. So almost 9...

X AI KOLs Timeline · 2026-05-23 Cached

The user shared their experience of writing academic papers entirely using AI (DeepSeek R1 and V4), emphasizing that the Chinese outline and fine prompt tuning are key, and noting that manually editing AI-generated writing is more tiring than writing it themselves.

0 favorites 0 likes
#academic-paper

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents

arXiv cs.AI · 2026-05-22 Cached

This paper introduces AgentAtlas, a framework that goes beyond outcome-only leaderboards for LLM agents by proposing a six-state control-decision taxonomy and a nine-category trajectory-failure taxonomy to evaluate agent behavior more comprehensively.

0 favorites 0 likes
#academic-paper

Evaluation of Chunking Strategies for Effective Text Embedding in Low-Resource Language on Agricultural Documents

arXiv cs.CL · 2026-05-22 Cached

This paper evaluates four text chunking strategies for Retrieval-Augmented Generation on Khmer agricultural documents, finding that character-based Recursive chunking with 300 characters yields the best retrieval and relevance performance.

0 favorites 0 likes
#academic-paper

DeepSlide: From Artifacts to Presentation Delivery

arXiv cs.AI · 2026-05-18 Cached

DeepSlide is a human-in-the-loop multi-agent system for the full presentation process, from requirement elicitation and time-budgeted narrative planning to evidence-grounded slide-script generation and rehearsal support. It introduces a dual-scoreboard benchmark separating static artifact quality from dynamic delivery excellence, and achieves gains in narrative flow, pacing precision, and slide-script synergy.

0 favorites 0 likes
#academic-paper

SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees

arXiv cs.LG · 2026-05-08 Cached

This paper introduces Sequential Agent Tuning (SAT), a coordinator-free training paradigm for multi-LLM teams that provides monotonic improvement guarantees and plug-and-play invariance, enabling smaller models to outperform larger ones.

0 favorites 0 likes
← Back to home

Submit Feedback